Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.4314. Min Act: -0.1700
Data Index: 8499853 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.2751. Min Act: -0.1700
Data Index: 1324132 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.1189. Min Act: -0.1700
Data Index: 3859683 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.0564. Min Act: -0.1700
Data Index: 6260780 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.0564. Min Act: -0.1700
Data Index: 3568676 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.0251. Min Act: -0.1700
Data Index: 540705 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.0251. Min Act: -0.1700
Data Index: 7086171 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4314. Min Range: -7.4314
Max Act: 7.0564. Min Act: -0.1700
Data Index: 2876201 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.9626. Min Act: -0.1700
Data Index: 8082803 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.9001. Min Act: -0.1700
Data Index: 859656 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.9314. Min Act: -0.1700
Data Index: 5104246 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.9001. Min Act: -0.1700
Data Index: 6159029 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.9001. Min Act: -0.1700
Data Index: 6032949 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8689. Min Act: -0.1700
Data Index: 5190748 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8376. Min Act: -0.1700
Data Index: 3641160 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8376. Min Act: -0.1700
Data Index: 4976719 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8064. Min Act: -0.1700
Data Index: 4954741 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8064. Min Act: -0.1700
Data Index: 7885921 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8064. Min Act: -0.1700
Data Index: 4464913 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4314. Min Range: -7.4314
Max Act: 6.8064. Min Act: -0.1700
Data Index: 6662170 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19