Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 136 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.9088. Min Act: -0.1700
Data Index: 8701890 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 2156442 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.6276. Min Act: -0.1700
Data Index: 6352421 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.6276. Min Act: -0.1700
Data Index: 2105153 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.5963. Min Act: -0.1700
Data Index: 4635710 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.5963. Min Act: -0.1700
Data Index: 3631309 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.5026. Min Act: -0.1700
Data Index: 8239495 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.5338. Min Act: -0.1700
Data Index: 2154341 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.5026. Min Act: -0.1700
Data Index: 359660 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.4713. Min Act: -0.1700
Data Index: 8218355 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.4088. Min Act: -0.1700
Data Index: 6171913 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.4088. Min Act: -0.1700
Data Index: 4294824 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.4088. Min Act: -0.1700
Data Index: 172932 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.4088. Min Act: -0.1700
Data Index: 2095301 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3776. Min Act: -0.1700
Data Index: 3869888 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3776. Min Act: -0.1700
Data Index: 1658229 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3776. Min Act: -0.1700
Data Index: 4420965 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3463. Min Act: -0.1700
Data Index: 1473572 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3463. Min Act: -0.1700
Data Index: 2918440 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9088. Min Range: -4.9088
Max Act: 4.3463. Min Act: -0.1700
Data Index: 8158395 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19