Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.1941. Min Act: -0.1700
Data Index: 985986 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.1316. Min Act: -0.1700
Data Index: 7340889 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0379. Min Act: -0.1700
Data Index: 2068447 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 6078755 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0379. Min Act: -0.1700
Data Index: 6627194 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0379. Min Act: -0.1700
Data Index: 5606217 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 5399930 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 3224292 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 4928999 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 3506110 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 7046063 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 8826206 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 7340887 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 2640943 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 6950426 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9754. Min Act: -0.1700
Data Index: 3320584 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4057792 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6345027 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 3162005 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 7340886 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19