Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.6345. Min Act: -0.1700
Data Index: 7838854 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.5876. Min Act: -0.1700
Data Index: 4654466 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.4936. Min Act: -0.1700
Data Index: 3182480 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3996. Min Act: -0.1700
Data Index: 5158574 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.4153. Min Act: -0.1700
Data Index: 4571698 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.4153. Min Act: -0.1700
Data Index: 1541073 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3996. Min Act: -0.1700
Data Index: 5848249 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3839. Min Act: -0.1700
Data Index: 7175360 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3055. Min Act: -0.1700
Data Index: 4933388 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.4153. Min Act: -0.1700
Data Index: 5249692 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3526. Min Act: -0.1700
Data Index: 1677600 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3526. Min Act: -0.1700
Data Index: 1443849 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3526. Min Act: -0.1700
Data Index: 645610 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3369. Min Act: -0.1700
Data Index: 4218386 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3526. Min Act: -0.1700
Data Index: 5217936 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3369. Min Act: -0.1700
Data Index: 1126014 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3212. Min Act: -0.1700
Data Index: 2635489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3682. Min Act: -0.1700
Data Index: 525242 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3055. Min Act: -0.1700
Data Index: 4016496 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6345. Min Range: -3.6345
Max Act: 3.3682. Min Act: -0.1700
Data Index: 1071641 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19