Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.5346. Min Act: -0.1700
Data Index: 8536599 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.4721. Min Act: -0.1700
Data Index: 380144 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.5034. Min Act: -0.1700
Data Index: 6719075 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.4409. Min Act: -0.1700
Data Index: 5128108 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.4096. Min Act: -0.1700
Data Index: 3940566 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.4096. Min Act: -0.1700
Data Index: 4418762 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3784. Min Act: -0.1700
Data Index: 3313546 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3784. Min Act: -0.1700
Data Index: 1749016 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3784. Min Act: -0.1700
Data Index: 8801664 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3471. Min Act: -0.1700
Data Index: 3610673 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3471. Min Act: -0.1700
Data Index: 5327520 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3159. Min Act: -0.1700
Data Index: 2801825 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3159. Min Act: -0.1700
Data Index: 3930487 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.3159. Min Act: -0.1700
Data Index: 2521414 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2846. Min Act: -0.1700
Data Index: 2727637 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2846. Min Act: -0.1700
Data Index: 5378209 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2534. Min Act: -0.1700
Data Index: 1306976 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2534. Min Act: -0.1700
Data Index: 4744840 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2534. Min Act: -0.1700
Data Index: 2754094 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5346. Min Range: -6.5346
Max Act: 6.2846. Min Act: -0.1700
Data Index: 5398005 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19