Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2126 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.8505. Min Act: -0.1700
Data Index: 5079539 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.6630. Min Act: -0.1700
Data Index: 5963979 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.6630. Min Act: -0.1700
Data Index: 8776124 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.6317. Min Act: -0.1700
Data Index: 6461643 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.6630. Min Act: -0.1700
Data Index: 363941 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.6005. Min Act: -0.1700
Data Index: 7943842 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3387322 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5692. Min Act: -0.1700
Data Index: 1472217 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5692. Min Act: -0.1700
Data Index: 8539084 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5380. Min Act: -0.1700
Data Index: 1963525 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5380. Min Act: -0.1700
Data Index: 8258735 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5067. Min Act: -0.1700
Data Index: 7398985 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5067. Min Act: -0.1700
Data Index: 3504614 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5067. Min Act: -0.1700
Data Index: 8523704 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.5067. Min Act: -0.1700
Data Index: 8523705 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.4755. Min Act: -0.1700
Data Index: 5852225 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.4755. Min Act: -0.1700
Data Index: 7807340 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.4755. Min Act: -0.1700
Data Index: 4080529 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.4442. Min Act: -0.1700
Data Index: 8211139 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8505. Min Range: -4.8505
Max Act: 4.4442. Min Act: -0.1700
Data Index: 8523703 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19