Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 464 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9994. Min Act: -0.1700
Data Index: 7718565 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9682. Min Act: -0.1700
Data Index: 8463846 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9369. Min Act: -0.1700
Data Index: 5302729 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9369. Min Act: -0.1700
Data Index: 7626710 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9057. Min Act: -0.1700
Data Index: 3827628 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9057. Min Act: -0.1700
Data Index: 2827384 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9057. Min Act: -0.1700
Data Index: 8379899 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8744. Min Act: -0.1700
Data Index: 3666087 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8744. Min Act: -0.1700
Data Index: 240694 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1912602 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8744. Min Act: -0.1700
Data Index: 8665349 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8744. Min Act: -0.1700
Data Index: 567078 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.9057. Min Act: -0.1700
Data Index: 2435377 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8431. Min Act: -0.1700
Data Index: 4851871 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8119. Min Act: -0.1700
Data Index: 8025727 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8431. Min Act: -0.1700
Data Index: 7874762 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8431. Min Act: -0.1700
Data Index: 6207652 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8119. Min Act: -0.1700
Data Index: 697885 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8119. Min Act: -0.1700
Data Index: 1226505 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9994. Min Range: -3.9994
Max Act: 3.8119. Min Act: -0.1700
Data Index: 2295320 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19