Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3403. Min Range: -9.3403
Max Act: 9.3403. Min Act: -0.1700
Data Index: 8603351 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3403. Min Range: -9.3403
Max Act: 9.2153. Min Act: -0.1700
Data Index: 7269881 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3403. Min Range: -9.3403
Max Act: 9.0278. Min Act: -0.1700
Data Index: 7904061 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.9028. Min Act: -0.1700
Data Index: 5443417 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.7778. Min Act: -0.1700
Data Index: 1898067 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.7778. Min Act: -0.1700
Data Index: 610621 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.7778. Min Act: -0.1700
Data Index: 2129095 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.7153. Min Act: -0.1700
Data Index: 5711566 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.7153. Min Act: -0.1700
Data Index: 7652523 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.6528. Min Act: -0.1700
Data Index: 5753666 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5903. Min Act: -0.1700
Data Index: 7160810 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.6528. Min Act: -0.1700
Data Index: 8800452 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5903. Min Act: -0.1700
Data Index: 6737044 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 3103426 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 3849476 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 3541738 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 2838217 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 7554171 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.5278. Min Act: -0.1700
Data Index: 5229982 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3403. Min Range: -9.3403
Max Act: 8.4653. Min Act: -0.1700
Data Index: 7492621 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19