Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1366 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.7660. Min Act: -0.1700
Data Index: 6703417 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.5160. Min Act: -0.1700
Data Index: 8760022 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.2660. Min Act: -0.1700
Data Index: 8265018 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.2347. Min Act: -0.1700
Data Index: 8342501 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.1722. Min Act: -0.1700
Data Index: 7316534 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.1722. Min Act: -0.1700
Data Index: 4323353 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.1097. Min Act: -0.1700
Data Index: 5268511 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.1097. Min Act: -0.1700
Data Index: 8342499 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.1097. Min Act: -0.1700
Data Index: 875550 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.0472. Min Act: -0.1700
Data Index: 656229 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.0472. Min Act: -0.1700
Data Index: 2215548 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.0160. Min Act: -0.1700
Data Index: 5636062 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7660. Min Range: -7.7660
Max Act: 7.0160. Min Act: -0.1700
Data Index: 6266159 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9535. Min Act: -0.1700
Data Index: 8279041 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9535. Min Act: -0.1700
Data Index: 4512025 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9535. Min Act: -0.1700
Data Index: 4138283 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9222. Min Act: -0.1700
Data Index: 6702449 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9222. Min Act: -0.1700
Data Index: 2899104 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9222. Min Act: -0.1700
Data Index: 3890345 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7660. Min Range: -7.7660
Max Act: 6.9222. Min Act: -0.1700
Data Index: 6225441 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19