Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.7705. Min Act: -0.1700
Data Index: 1367703 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.7705. Min Act: -0.1700
Data Index: 3968942 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.4580. Min Act: -0.1700
Data Index: 557622 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.3330. Min Act: -0.1700
Data Index: 263104 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.2080. Min Act: -0.1700
Data Index: 6760161 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.1455. Min Act: -0.1700
Data Index: 557624 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.0830. Min Act: -0.1700
Data Index: 4735125 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.0205. Min Act: -0.1700
Data Index: 7998334 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7705. Min Range: -8.7705
Max Act: 8.0205. Min Act: -0.1700
Data Index: 363907 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.8955. Min Act: -0.1700
Data Index: 3990360 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.8018. Min Act: -0.1700
Data Index: 8406600 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.7705. Min Act: -0.1700
Data Index: 6342059 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.5518. Min Act: -0.1700
Data Index: 3817947 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.6143. Min Act: -0.1700
Data Index: 8212060 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.5518. Min Act: -0.1700
Data Index: 3671983 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.4580. Min Act: -0.1700
Data Index: 3685490 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.4893. Min Act: -0.1700
Data Index: 6904730 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.4893. Min Act: -0.1700
Data Index: 4749493 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.4268. Min Act: -0.1700
Data Index: 6215571 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7705. Min Range: -8.7705
Max Act: 7.3643. Min Act: -0.1700
Data Index: 7275320 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19