Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.9069. Min Act: -0.1700
Data Index: 3645871 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.7506. Min Act: -0.1700
Data Index: 8501603 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.7194. Min Act: -0.1700
Data Index: 1935638 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.6569. Min Act: -0.1700
Data Index: 5760725 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.6256. Min Act: -0.1700
Data Index: 6917831 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.6256. Min Act: -0.1700
Data Index: 1425548 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5944. Min Act: -0.1700
Data Index: 4788049 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5944. Min Act: -0.1700
Data Index: 6627020 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5944. Min Act: -0.1700
Data Index: 3488537 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5944. Min Act: -0.1700
Data Index: 7991775 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5631. Min Act: -0.1700
Data Index: 679011 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5319. Min Act: -0.1700
Data Index: 5421301 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5319. Min Act: -0.1700
Data Index: 178710 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5319. Min Act: -0.1700
Data Index: 1371273 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5319. Min Act: -0.1700
Data Index: 8013463 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5006. Min Act: -0.1700
Data Index: 4096883 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.5006. Min Act: -0.1700
Data Index: 5793907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.4694. Min Act: -0.1700
Data Index: 109684 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.4694. Min Act: -0.1700
Data Index: 240543 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9069. Min Range: -4.9069
Max Act: 4.4694. Min Act: -0.1700
Data Index: 7302424 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19