Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1598. Min Range: -5.1598
Max Act: 5.1598. Min Act: -0.1700
Data Index: 2347076 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1598. Min Range: -5.1598
Max Act: 5.0973. Min Act: -0.1700
Data Index: 2347079 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.9411. Min Act: -0.1700
Data Index: 5669817 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.9411. Min Act: -0.1700
Data Index: 6468979 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.9411. Min Act: -0.1700
Data Index: 2170744 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.9098. Min Act: -0.1700
Data Index: 7080883 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8786. Min Act: -0.1700
Data Index: 774662 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.9098. Min Act: -0.1700
Data Index: 700755 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8473. Min Act: -0.1700
Data Index: 5669814 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8473. Min Act: -0.1700
Data Index: 3950055 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8473. Min Act: -0.1700
Data Index: 4308700 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8473. Min Act: -0.1700
Data Index: 774661 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3293158 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3345861 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3239553 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.8161. Min Act: -0.1700
Data Index: 774663 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.7536. Min Act: -0.1700
Data Index: 4857574 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.7536. Min Act: -0.1700
Data Index: 2522755 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.7223. Min Act: -0.1700
Data Index: 3700613 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1598. Min Range: -5.1598
Max Act: 4.7536. Min Act: -0.1700
Data Index: 338184 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19