Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.2990. Min Act: -0.1700
Data Index: 6334733 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.2677. Min Act: -0.1700
Data Index: 8630815 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.2677. Min Act: -0.1700
Data Index: 2716429 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.2365. Min Act: -0.1700
Data Index: 6475131 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.2365. Min Act: -0.1700
Data Index: 2495697 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1740. Min Act: -0.1700
Data Index: 5474384 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1740. Min Act: -0.1700
Data Index: 7588855 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1115. Min Act: -0.1700
Data Index: 6174835 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1115. Min Act: -0.1700
Data Index: 3366110 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1115. Min Act: -0.1700
Data Index: 1980788 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.0490. Min Act: -0.1700
Data Index: 8649680 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.0802. Min Act: -0.1700
Data Index: 8598098 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.1115. Min Act: -0.1700
Data Index: 6381372 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.0802. Min Act: -0.1700
Data Index: 1001547 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.0490. Min Act: -0.1700
Data Index: 5106220 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2990. Min Range: -5.2990
Max Act: 5.0177. Min Act: -0.1700
Data Index: 2903517 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2990. Min Range: -5.2990
Max Act: 4.9552. Min Act: -0.1700
Data Index: 343753 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2990. Min Range: -5.2990
Max Act: 4.9865. Min Act: -0.1700
Data Index: 7356893 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2990. Min Range: -5.2990
Max Act: 4.9865. Min Act: -0.1700
Data Index: 6175736 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2990. Min Range: -5.2990
Max Act: 4.9552. Min Act: -0.1700
Data Index: 2830417 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19