Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.9930. Min Act: -0.1700
Data Index: 4554199 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.7430. Min Act: -0.1700
Data Index: 8475354 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7511951 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3419369 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.7117. Min Act: -0.1700
Data Index: 7494407 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6492. Min Act: -0.1700
Data Index: 5398910 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6492. Min Act: -0.1700
Data Index: 6248094 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6492. Min Act: -0.1700
Data Index: 7358117 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6180. Min Act: -0.1700
Data Index: 8602362 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6180. Min Act: -0.1700
Data Index: 304091 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.6180. Min Act: -0.1700
Data Index: 6606343 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.5867. Min Act: -0.1700
Data Index: 440361 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5072774 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8754800 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.5555. Min Act: -0.1700
Data Index: 5641567 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.5555. Min Act: -0.1700
Data Index: 5490972 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.4930. Min Act: -0.1700
Data Index: 2951045 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.4930. Min Act: -0.1700
Data Index: 5124971 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.4617. Min Act: -0.1700
Data Index: 3757853 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9930. Min Range: -5.9930
Max Act: 5.4305. Min Act: -0.1700
Data Index: 5612496 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19