Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.7534. Min Act: -0.1700
Data Index: 8316655 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7290187 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.6126. Min Act: -0.1700
Data Index: 6584870 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5813. Min Act: -0.1700
Data Index: 2235477 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5813. Min Act: -0.1700
Data Index: 6188521 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5500. Min Act: -0.1700
Data Index: 7564498 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5500. Min Act: -0.1700
Data Index: 4895977 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5343. Min Act: -0.1700
Data Index: 7821821 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5343. Min Act: -0.1700
Data Index: 1370183 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5343. Min Act: -0.1700
Data Index: 2370776 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5343. Min Act: -0.1700
Data Index: 3985784 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5186. Min Act: -0.1700
Data Index: 3214096 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5343. Min Act: -0.1700
Data Index: 5300020 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.5030. Min Act: -0.1700
Data Index: 6222783 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4873. Min Act: -0.1700
Data Index: 3997203 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4873. Min Act: -0.1700
Data Index: 3299164 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4873. Min Act: -0.1700
Data Index: 8371757 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4717. Min Act: -0.1700
Data Index: 8690525 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4717. Min Act: -0.1700
Data Index: 6394987 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7534. Min Range: -3.7534
Max Act: 3.4560. Min Act: -0.1700
Data Index: 7666900 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19