Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.5313. Min Act: -0.1700
Data Index: 737027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.4688. Min Act: -0.1699
Data Index: 2954099 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.4063. Min Act: -0.1700
Data Index: 8403397 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.3438. Min Act: -0.1700
Data Index: 4270132 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.3126. Min Act: -0.1700
Data Index: 6491080 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.3126. Min Act: -0.1700
Data Index: 4569078 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2813. Min Act: -0.1700
Data Index: 2857915 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2813. Min Act: -0.1700
Data Index: 2433998 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2813. Min Act: -0.1700
Data Index: 7090887 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.3126. Min Act: -0.1700
Data Index: 6028804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 1166128 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 1724113 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 7990266 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 6669717 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5274453 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5864284 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2501. Min Act: -0.1700
Data Index: 909721 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2188. Min Act: -0.1700
Data Index: 3077708 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2188. Min Act: -0.1700
Data Index: 1523898 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5313. Min Range: -5.5313
Max Act: 5.2188. Min Act: -0.1700
Data Index: 5968988 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19