Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.6099. Min Act: -0.1700
Data Index: 8487568 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5630. Min Act: -0.1700
Data Index: 19335 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5630. Min Act: -0.1700
Data Index: 137969 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5473. Min Act: -0.1700
Data Index: 3681605 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5317. Min Act: -0.1700
Data Index: 8033 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5473. Min Act: -0.1700
Data Index: 7490191 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5317. Min Act: -0.1700
Data Index: 4908972 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5160. Min Act: -0.1700
Data Index: 8750775 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.5160. Min Act: -0.1700
Data Index: 5819376 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4847. Min Act: -0.1700
Data Index: 7568414 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4533. Min Act: -0.1700
Data Index: 1496873 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4377. Min Act: -0.1700
Data Index: 2666976 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4690. Min Act: -0.1700
Data Index: 3912436 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4533. Min Act: -0.1700
Data Index: 634515 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4533. Min Act: -0.1700
Data Index: 5786676 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4377. Min Act: -0.1700
Data Index: 7610844 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4690. Min Act: -0.1700
Data Index: 7909437 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4220. Min Act: -0.1700
Data Index: 233387 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4377. Min Act: -0.1700
Data Index: 4465058 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6099. Min Range: -3.6099
Max Act: 3.4377. Min Act: -0.1700
Data Index: 2974480 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19