Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.4088. Min Act: -0.1700
Data Index: 2339660 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.3775. Min Act: -0.1700
Data Index: 8777523 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.3463. Min Act: -0.1700
Data Index: 3548691 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.2525. Min Act: -0.1700
Data Index: 7875774 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1900. Min Act: -0.1700
Data Index: 2699216 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4769134 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 4124470 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5153037 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 5791765 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5457833 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 6903352 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2839021 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 5018961 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 5930046 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 7027423 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 6988426 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 2160608 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0025. Min Act: -0.1700
Data Index: 6494467 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0025. Min Act: -0.1700
Data Index: 7929901 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0025. Min Act: -0.1700
Data Index: 6678426 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19