Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0085. Min Range: -4.0085
Max Act: 4.0085. Min Act: -0.1700
Data Index: 8470686 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.8522. Min Act: -0.1700
Data Index: 4727945 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.8053. Min Act: -0.1700
Data Index: 439614 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.8209. Min Act: -0.1700
Data Index: 1553183 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.8053. Min Act: -0.1700
Data Index: 7508235 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.8053. Min Act: -0.1700
Data Index: 1937440 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7740. Min Act: -0.1700
Data Index: 6784069 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7740. Min Act: -0.1700
Data Index: 2600710 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7740. Min Act: -0.1700
Data Index: 5783992 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7583. Min Act: -0.1700
Data Index: 6536223 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7583. Min Act: -0.1700
Data Index: 2772443 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7583. Min Act: -0.1700
Data Index: 7704688 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7427. Min Act: -0.1700
Data Index: 4746220 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7271. Min Act: -0.1700
Data Index: 8532729 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7271. Min Act: -0.1700
Data Index: 1963167 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.7114. Min Act: -0.1700
Data Index: 8625499 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.6801. Min Act: -0.1700
Data Index: 8458389 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.6958. Min Act: -0.1700
Data Index: 1054221 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.6958. Min Act: -0.1700
Data Index: 4882320 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0085. Min Range: -4.0085
Max Act: 3.6801. Min Act: -0.1700
Data Index: 749664 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19