Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0981. Min Range: -6.0981
Max Act: 6.0981. Min Act: -0.1700
Data Index: 3760925 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.8793. Min Act: -0.1700
Data Index: 3363802 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.8481. Min Act: -0.1700
Data Index: 2479802 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.7543. Min Act: -0.1700
Data Index: 2044434 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.7543. Min Act: -0.1700
Data Index: 5284875 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6237401 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5028960 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.6293. Min Act: -0.1700
Data Index: 1694477 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7784741 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.6293. Min Act: -0.1700
Data Index: 4695677 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5981. Min Act: -0.1700
Data Index: 429779 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5668. Min Act: -0.1700
Data Index: 8354285 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5668. Min Act: -0.1700
Data Index: 5349578 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 6169055 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 3379543 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 8128519 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 7995981 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5866025 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5356. Min Act: -0.1700
Data Index: 8444927 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0981. Min Range: -6.0981
Max Act: 5.5043. Min Act: -0.1700
Data Index: 7909055 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19