Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.8885. Min Act: -0.1700
Data Index: 6244963 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6004426 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7634. Min Act: -0.1700
Data Index: 692137 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7634. Min Act: -0.1700
Data Index: 2218912 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7321. Min Act: -0.1700
Data Index: 5380444 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7321. Min Act: -0.1700
Data Index: 6367182 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.7321. Min Act: -0.1700
Data Index: 8320614 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6695. Min Act: -0.1700
Data Index: 1853070 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6695. Min Act: -0.1700
Data Index: 1476979 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6695. Min Act: -0.1700
Data Index: 79105 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6695. Min Act: -0.1700
Data Index: 2456017 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6695. Min Act: -0.1700
Data Index: 2147039 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6382. Min Act: -0.1700
Data Index: 7495096 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6069. Min Act: -0.1700
Data Index: 548957 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6382. Min Act: -0.1700
Data Index: 4848259 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6382. Min Act: -0.1700
Data Index: 334286 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6069. Min Act: -0.1700
Data Index: 6955272 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6069. Min Act: -0.1700
Data Index: 6787517 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.6069. Min Act: -0.1700
Data Index: 4861252 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8885. Min Range: -3.8885
Max Act: 3.5756. Min Act: -0.1700
Data Index: 2526289 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19