Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.2192. Min Act: -0.1700
Data Index: 3678678 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.2504. Min Act: -0.1700
Data Index: 3596909 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.0942. Min Act: -0.1700
Data Index: 3844631 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.0942. Min Act: -0.1700
Data Index: 1111117 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.0317. Min Act: -0.1700
Data Index: 4455873 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.0317. Min Act: -0.1700
Data Index: 4831130 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2504. Min Range: -7.2504
Max Act: 7.0004. Min Act: -0.1700
Data Index: 2300319 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9692. Min Act: -0.1700
Data Index: 8563607 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6546011 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3420215 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9692. Min Act: -0.1700
Data Index: 4375185 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9067. Min Act: -0.1700
Data Index: 792099 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 1671771 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 2541463 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9692. Min Act: -0.1700
Data Index: 5395397 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 2456506 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9379. Min Act: -0.1700
Data Index: 1334022 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.8754. Min Act: -0.1700
Data Index: 6166001 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9067. Min Act: -0.1700
Data Index: 77351 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2504. Min Range: -7.2504
Max Act: 6.9067. Min Act: -0.1700
Data Index: 2212954 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19