Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.1707. Min Range: -11.1707
Max Act: 11.1707. Min Act: -0.1700
Data Index: 877777 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1707. Min Range: -11.1707
Max Act: 11.0457. Min Act: -0.1700
Data Index: 1322408 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1707. Min Range: -11.1707
Max Act: 11.0457. Min Act: -0.1700
Data Index: 8302654 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.9832. Min Act: -0.1700
Data Index: 2492044 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.9207. Min Act: -0.1700
Data Index: 3903139 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.8582. Min Act: -0.1700
Data Index: 5156555 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.8582. Min Act: -0.1700
Data Index: 5090976 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.9207. Min Act: -0.1700
Data Index: 5751702 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.8582. Min Act: -0.1700
Data Index: 7545857 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7957. Min Act: -0.1700
Data Index: 260257 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7957. Min Act: -0.1700
Data Index: 6461660 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7957. Min Act: -0.1700
Data Index: 3712030 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 1155328 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 3810921 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.6707. Min Act: -0.1700
Data Index: 7270429 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 4654338 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 1094281 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.6707. Min Act: -0.1700
Data Index: 1510447 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 5487483 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1707. Min Range: -11.1707
Max Act: 10.7332. Min Act: -0.1700
Data Index: 5103990 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19