Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.8459. Min Act: -0.1700
Data Index: 161774 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.5959. Min Act: -0.1700
Data Index: 3037956 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.4084. Min Act: -0.1700
Data Index: 7556990 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.4084. Min Act: -0.1700
Data Index: 3646431 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.4084. Min Act: -0.1700
Data Index: 8420842 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.4084. Min Act: -0.1700
Data Index: 2540433 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.3772. Min Act: -0.1700
Data Index: 7998053 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.3459. Min Act: -0.1700
Data Index: 3394502 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.3459. Min Act: -0.1700
Data Index: 4501645 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.2522. Min Act: -0.1700
Data Index: 7359298 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.1897. Min Act: -0.1700
Data Index: 6855729 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.2209. Min Act: -0.1700
Data Index: 2568338 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.1897. Min Act: -0.1700
Data Index: 1560981 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.2209. Min Act: -0.1700
Data Index: 405489 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.1897. Min Act: -0.1700
Data Index: 3354338 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.1897. Min Act: -0.1700
Data Index: 2624561 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.2209. Min Act: -0.1700
Data Index: 4070420 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.1584. Min Act: -0.1700
Data Index: 4540129 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3626162 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8459. Min Range: -6.8459
Max Act: 6.0647. Min Act: -0.1700
Data Index: 4986673 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19