Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2601. Min Range: -12.2601
Max Act: 12.2601. Min Act: -0.1700
Data Index: 6691607 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2601. Min Range: -12.2601
Max Act: 12.1976. Min Act: -0.1700
Data Index: 572788 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2601. Min Range: -12.2601
Max Act: 12.0101. Min Act: -0.1700
Data Index: 5442465 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.8851. Min Act: -0.1700
Data Index: 6848366 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.6351. Min Act: -0.1700
Data Index: 4241383 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.6351. Min Act: -0.1700
Data Index: 578999 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.6351. Min Act: -0.1700
Data Index: 5893261 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.5726. Min Act: -0.1700
Data Index: 8008489 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.5726. Min Act: -0.1700
Data Index: 2690052 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.5726. Min Act: -0.1700
Data Index: 1817645 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.5101. Min Act: -0.1700
Data Index: 3520898 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.5101. Min Act: -0.1700
Data Index: 2216543 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.4476. Min Act: -0.1700
Data Index: 2162201 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3851. Min Act: -0.1700
Data Index: 5284806 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3851. Min Act: -0.1700
Data Index: 5942980 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3851. Min Act: -0.1700
Data Index: 6160427 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3226. Min Act: -0.1700
Data Index: 4600039 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3226. Min Act: -0.1700
Data Index: 2323847 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3226. Min Act: -0.1700
Data Index: 5018830 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2601. Min Range: -12.2601
Max Act: 11.3226. Min Act: -0.1700
Data Index: 6587111 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19