Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.7928. Min Act: -0.1700
Data Index: 3159456 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.6207. Min Act: -0.1700
Data Index: 4289768 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.5581. Min Act: -0.1700
Data Index: 3347338 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.5111. Min Act: -0.1700
Data Index: 5267346 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.5111. Min Act: -0.1700
Data Index: 628148 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4485. Min Act: -0.1700
Data Index: 5360783 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4171. Min Act: -0.1700
Data Index: 1660461 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4328. Min Act: -0.1700
Data Index: 1518528 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4171. Min Act: -0.1700
Data Index: 1188833 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4015. Min Act: -0.1700
Data Index: 8071317 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.4015. Min Act: -0.1700
Data Index: 1531339 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3858. Min Act: -0.1700
Data Index: 7169335 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3701. Min Act: -0.1700
Data Index: 7237272 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3701. Min Act: -0.1700
Data Index: 1171998 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3544. Min Act: -0.1700
Data Index: 2592382 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3544. Min Act: -0.1700
Data Index: 1551794 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3544. Min Act: -0.1700
Data Index: 8779441 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3387. Min Act: -0.1700
Data Index: 3271745 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3073. Min Act: -0.1700
Data Index: 3458070 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7928. Min Range: -3.7928
Max Act: 3.3073. Min Act: -0.1700
Data Index: 3619855 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19