Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1270 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1174. Min Range: -7.1174
Max Act: 7.1174. Min Act: -0.1700
Data Index: 938046 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1174. Min Range: -7.1174
Max Act: 7.0549. Min Act: -0.1700
Data Index: 7364644 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.8361. Min Act: -0.1700
Data Index: 8648445 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.8674. Min Act: -0.1700
Data Index: 643856 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.8049. Min Act: -0.1700
Data Index: 3880100 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.7736. Min Act: -0.1700
Data Index: 7203566 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.7736. Min Act: -0.1700
Data Index: 5152450 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.7424. Min Act: -0.1700
Data Index: 5382651 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.7111. Min Act: -0.1700
Data Index: 5348489 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.7111. Min Act: -0.1700
Data Index: 741053 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6486. Min Act: -0.1700
Data Index: 353940 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6486. Min Act: -0.1700
Data Index: 3710266 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6799. Min Act: -0.1700
Data Index: 5853000 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6799. Min Act: -0.1700
Data Index: 1070695 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6486. Min Act: -0.1700
Data Index: 628907 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6486. Min Act: -0.1700
Data Index: 2043005 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6486. Min Act: -0.1700
Data Index: 1769073 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6174. Min Act: -0.1700
Data Index: 5571084 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.6174. Min Act: -0.1700
Data Index: 4600512 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1174. Min Range: -7.1174
Max Act: 6.5861. Min Act: -0.1700
Data Index: 1583704 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19