Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.3248. Min Act: -0.1700
Data Index: 6610393 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.2310. Min Act: -0.1700
Data Index: 8555771 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1998. Min Act: -0.1700
Data Index: 1603352 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1685. Min Act: -0.1700
Data Index: 4270051 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1373. Min Act: -0.1700
Data Index: 1708104 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1373. Min Act: -0.1700
Data Index: 2328741 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1373. Min Act: -0.1700
Data Index: 692629 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.1060. Min Act: -0.1700
Data Index: 3912798 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0747. Min Act: -0.1700
Data Index: 6073677 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0435. Min Act: -0.1700
Data Index: 3760287 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0435. Min Act: -0.1700
Data Index: 3812862 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0122. Min Act: -0.1700
Data Index: 4020230 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0435. Min Act: -0.1700
Data Index: 3177402 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0122. Min Act: -0.1700
Data Index: 7885622 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0435. Min Act: -0.1700
Data Index: 6609735 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3248. Min Range: -4.3248
Max Act: 3.9810. Min Act: -0.1700
Data Index: 4441506 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0435. Min Act: -0.1700
Data Index: 2547427 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0122. Min Act: -0.1700
Data Index: 1464092 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3248. Min Range: -4.3248
Max Act: 3.9810. Min Act: -0.1700
Data Index: 899516 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3248. Min Range: -4.3248
Max Act: 4.0122. Min Act: -0.1700
Data Index: 2290589 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19