Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.9268. Min Act: -0.1700
Data Index: 7295575 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.6143. Min Act: -0.1700
Data Index: 4280344 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.6143. Min Act: -0.1700
Data Index: 5388118 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.6143. Min Act: -0.1700
Data Index: 1807763 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.5830. Min Act: -0.1700
Data Index: 35910 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.5518. Min Act: -0.1700
Data Index: 5064116 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.5205. Min Act: -0.1700
Data Index: 8536336 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.5518. Min Act: -0.1700
Data Index: 5654681 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.4893. Min Act: -0.1700
Data Index: 2037379 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.4580. Min Act: -0.1700
Data Index: 520828 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.4580. Min Act: -0.1700
Data Index: 7791832 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.4268. Min Act: -0.1700
Data Index: 1067362 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3955. Min Act: -0.1700
Data Index: 680816 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3955. Min Act: -0.1700
Data Index: 5474291 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3955. Min Act: -0.1700
Data Index: 402248 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3643. Min Act: -0.1700
Data Index: 7442970 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3330. Min Act: -0.1700
Data Index: 3261316 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3330. Min Act: -0.1700
Data Index: 968172 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.3330. Min Act: -0.1700
Data Index: 5783938 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9268. Min Range: -7.9268
Max Act: 7.2705. Min Act: -0.1700
Data Index: 3689542 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19