Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.5430. Min Act: -0.1700
Data Index: 2023374 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.5117. Min Act: -0.1700
Data Index: 1332036 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4804. Min Act: -0.1700
Data Index: 2023376 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4804. Min Act: -0.1700
Data Index: 5605729 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4177. Min Act: -0.1700
Data Index: 1901436 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4177. Min Act: -0.1700
Data Index: 2210701 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4020. Min Act: -0.1700
Data Index: 1281990 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4020. Min Act: -0.1700
Data Index: 839289 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4020. Min Act: -0.1700
Data Index: 1306281 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.4177. Min Act: -0.1700
Data Index: 4581019 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3863. Min Act: -0.1700
Data Index: 6733230 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3863. Min Act: -0.1700
Data Index: 1338244 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3863. Min Act: -0.1700
Data Index: 6468482 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3707. Min Act: -0.1700
Data Index: 4410840 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3707. Min Act: -0.1700
Data Index: 765528 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3707. Min Act: -0.1700
Data Index: 2667737 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3707. Min Act: -0.1700
Data Index: 2662633 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3550. Min Act: -0.1700
Data Index: 4742605 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3707. Min Act: -0.1700
Data Index: 911053 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5430. Min Range: -3.5430
Max Act: 3.3550. Min Act: -0.1700
Data Index: 839288 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19