Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4887 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3284. Min Range: -4.3284
Max Act: 4.3284. Min Act: -0.1700
Data Index: 5880405 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3284. Min Range: -4.3284
Max Act: 4.2034. Min Act: -0.1700
Data Index: 3229432 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3284. Min Range: -4.3284
Max Act: 4.0784. Min Act: -0.1700
Data Index: 4100635 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3284. Min Range: -4.3284
Max Act: 4.0158. Min Act: -0.1700
Data Index: 829997 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3284. Min Range: -4.3284
Max Act: 4.0158. Min Act: -0.1700
Data Index: 4509871 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.9533. Min Act: -0.1700
Data Index: 7044598 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.9533. Min Act: -0.1700
Data Index: 1593025 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.9221. Min Act: -0.1700
Data Index: 7868859 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.9221. Min Act: -0.1700
Data Index: 5439851 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.8595. Min Act: -0.1700
Data Index: 8113477 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.8908. Min Act: -0.1700
Data Index: 2631271 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.8595. Min Act: -0.1700
Data Index: 1321055 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.8283. Min Act: -0.1700
Data Index: 3617743 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.8283. Min Act: -0.1700
Data Index: 4662696 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7970. Min Act: -0.1700
Data Index: 35219 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7657. Min Act: -0.1700
Data Index: 7544627 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7344. Min Act: -0.1700
Data Index: 6269782 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7344. Min Act: -0.1700
Data Index: 608032 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7344. Min Act: -0.1700
Data Index: 7155927 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3284. Min Range: -4.3284
Max Act: 3.7344. Min Act: -0.1700
Data Index: 3805236 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19