Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.6543. Min Act: -0.1700
Data Index: 4163790 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.5918. Min Act: -0.1700
Data Index: 6097175 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.6231. Min Act: -0.1700
Data Index: 321816 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.4981. Min Act: -0.1700
Data Index: 4163791 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 3624391 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.4668. Min Act: -0.1700
Data Index: 6189281 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.4356. Min Act: -0.1700
Data Index: 7988262 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3731. Min Act: -0.1700
Data Index: 5430601 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3418. Min Act: -0.1700
Data Index: 791088 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3106. Min Act: -0.1700
Data Index: 7900989 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3731. Min Act: -0.1700
Data Index: 7382478 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3106. Min Act: -0.1700
Data Index: 941562 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3106. Min Act: -0.1700
Data Index: 2661941 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3106. Min Act: -0.1700
Data Index: 148522 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.3106. Min Act: -0.1700
Data Index: 7255233 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.2793. Min Act: -0.1700
Data Index: 2805710 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.2481. Min Act: -0.1700
Data Index: 6778794 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.2793. Min Act: -0.1700
Data Index: 4446602 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.2481. Min Act: -0.1700
Data Index: 647207 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6543. Min Range: -6.6543
Max Act: 6.2481. Min Act: -0.1700
Data Index: 1972468 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19