Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1281. Min Range: -10.1281
Max Act: 10.1281. Min Act: -0.1700
Data Index: 7919142 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1281. Min Range: -10.1281
Max Act: 9.2531. Min Act: -0.1700
Data Index: 1700473 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1281. Min Range: -10.1281
Max Act: 8.5656. Min Act: -0.1700
Data Index: 2587296 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1281. Min Range: -10.1281
Max Act: 8.0656. Min Act: -0.1700
Data Index: 2217745 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.9406. Min Act: -0.1700
Data Index: 8469968 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.9094. Min Act: -0.1700
Data Index: 1741167 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.9094. Min Act: -0.1700
Data Index: 6384101 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8469. Min Act: -0.1700
Data Index: 1061501 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 7125185 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 4866447 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 5949042 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 8487917 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8469. Min Act: -0.1700
Data Index: 1514751 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 1811168 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.7531. Min Act: -0.1700
Data Index: 2131091 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.7219. Min Act: -0.1700
Data Index: 1589371 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.6906. Min Act: -0.1700
Data Index: 8621340 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.6594. Min Act: -0.1700
Data Index: 6851299 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.7219. Min Act: -0.1700
Data Index: 3810522 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1281. Min Range: -10.1281
Max Act: 7.6906. Min Act: -0.1700
Data Index: 8017418 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19