Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2278. Min Range: -8.2278
Max Act: 8.2278. Min Act: -0.1700
Data Index: 1473149 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.9153. Min Act: -0.1700
Data Index: 6405785 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.7903. Min Act: -0.1700
Data Index: 39982 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.8528. Min Act: -0.1700
Data Index: 3262548 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.8528. Min Act: -0.1700
Data Index: 799260 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.7903. Min Act: -0.1700
Data Index: 2399330 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.7278. Min Act: -0.1700
Data Index: 6527799 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.7278. Min Act: -0.1700
Data Index: 7336784 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.7278. Min Act: -0.1700
Data Index: 7628087 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6653. Min Act: -0.1700
Data Index: 1528232 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6653. Min Act: -0.1700
Data Index: 4264733 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6653. Min Act: -0.1700
Data Index: 7876941 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6653. Min Act: -0.1700
Data Index: 3975662 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1700
Data Index: 6166979 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1700
Data Index: 5293940 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1697
Data Index: 2600715 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1700
Data Index: 2410702 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1700
Data Index: 7699183 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.6028. Min Act: -0.1700
Data Index: 4433397 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2278. Min Range: -8.2278
Max Act: 7.5403. Min Act: -0.1700
Data Index: 2534780 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19