Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0002. Min Range: -7.0002
Max Act: 7.0002. Min Act: -0.1700
Data Index: 7274613 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.7814. Min Act: -0.1700
Data Index: 1625807 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.7814. Min Act: -0.1700
Data Index: 7936647 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.7189. Min Act: -0.1700
Data Index: 8214140 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.6252. Min Act: -0.1700
Data Index: 2111290 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.6252. Min Act: -0.1700
Data Index: 1002518 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5939. Min Act: -0.1700
Data Index: 3614857 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5939. Min Act: -0.1700
Data Index: 2002922 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5939. Min Act: -0.1700
Data Index: 3232595 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5939. Min Act: -0.1700
Data Index: 4925417 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5314. Min Act: -0.1700
Data Index: 1054354 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5314. Min Act: -0.1700
Data Index: 7856303 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5002. Min Act: -0.1700
Data Index: 119636 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.5002. Min Act: -0.1700
Data Index: 2460828 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.4689. Min Act: -0.1700
Data Index: 907063 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.4377. Min Act: -0.1700
Data Index: 3227475 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.4377. Min Act: -0.1700
Data Index: 2364477 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.4377. Min Act: -0.1700
Data Index: 2275876 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.4064. Min Act: -0.1700
Data Index: 6022736 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0002. Min Range: -7.0002
Max Act: 6.3752. Min Act: -0.1700
Data Index: 2711229 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19