Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.8694. Min Act: -0.1700
Data Index: 8502720 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.8382. Min Act: -0.1700
Data Index: 6175472 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.8382. Min Act: -0.1700
Data Index: 2009824 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7757. Min Act: -0.1700
Data Index: 6891441 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7757. Min Act: -0.1700
Data Index: 6105705 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7132. Min Act: -0.1700
Data Index: 7225105 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7132. Min Act: -0.1700
Data Index: 8791132 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7132. Min Act: -0.1700
Data Index: 3542232 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.7132. Min Act: -0.1700
Data Index: 7436078 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6819. Min Act: -0.1700
Data Index: 3453373 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6819. Min Act: -0.1700
Data Index: 7326178 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6819. Min Act: -0.1700
Data Index: 1277591 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6507. Min Act: -0.1700
Data Index: 5278471 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6194. Min Act: -0.1700
Data Index: 7453764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6507. Min Act: -0.1700
Data Index: 5770297 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6507. Min Act: -0.1700
Data Index: 7709543 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6507. Min Act: -0.1700
Data Index: 1655627 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6194. Min Act: -0.1700
Data Index: 6421296 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6194. Min Act: -0.1700
Data Index: 1998087 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8694. Min Range: -4.8694
Max Act: 4.6194. Min Act: -0.1700
Data Index: 6641930 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19