Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.7264. Min Act: -0.1700
Data Index: 5789906 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.1951. Min Act: -0.1700
Data Index: 3736505 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7264. Min Range: -7.7264
Max Act: 7.0701. Min Act: -0.1700
Data Index: 5406431 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.9451. Min Act: -0.1700
Data Index: 946790 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.9139. Min Act: -0.1700
Data Index: 4773739 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.8826. Min Act: -0.1700
Data Index: 5077521 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.7889. Min Act: -0.1700
Data Index: 6864027 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.7576. Min Act: -0.1700
Data Index: 2315517 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.6639. Min Act: -0.1700
Data Index: 7923605 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.6326. Min Act: -0.1700
Data Index: 537074 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.6014. Min Act: -0.1700
Data Index: 1521469 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.6014. Min Act: -0.1700
Data Index: 686639 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 4695539 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.5076. Min Act: -0.1700
Data Index: 5406428 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.5076. Min Act: -0.1700
Data Index: 1848979 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.4764. Min Act: -0.1700
Data Index: 5574947 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.4139. Min Act: -0.1700
Data Index: 6550192 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.4139. Min Act: -0.1700
Data Index: 3149352 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.3514. Min Act: -0.1700
Data Index: 8698049 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7264. Min Range: -7.7264
Max Act: 6.3514. Min Act: -0.1700
Data Index: 6314875 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19