Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.5215. Min Act: -0.1700
Data Index: 6767743 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.5527. Min Act: -0.1700
Data Index: 5118584 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.4277. Min Act: -0.1700
Data Index: 1434597 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.3652. Min Act: -0.1700
Data Index: 8818899 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.3652. Min Act: -0.1700
Data Index: 8608174 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.3340. Min Act: -0.1700
Data Index: 2187924 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.3340. Min Act: -0.1700
Data Index: 153203 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5760082 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2715. Min Act: -0.1700
Data Index: 2359979 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2715. Min Act: -0.1700
Data Index: 724037 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2090. Min Act: -0.1700
Data Index: 2774868 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2402. Min Act: -0.1700
Data Index: 68494 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5240414 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2715. Min Act: -0.1700
Data Index: 4314698 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2402. Min Act: -0.1700
Data Index: 4352805 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1786752 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2090. Min Act: -0.1700
Data Index: 8741350 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.2090. Min Act: -0.1700
Data Index: 5166133 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1864256 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5527. Min Range: -5.5527
Max Act: 5.1777. Min Act: -0.1700
Data Index: 169242 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19