Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.1496. Min Act: -0.1700
Data Index: 2470149 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.0491. Min Act: -0.1700
Data Index: 8777224 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.0323. Min Act: -0.1700
Data Index: 137620 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.0154. Min Act: -0.1700
Data Index: 676527 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.0154. Min Act: -0.1700
Data Index: 3712109 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1496. Min Range: -2.1496
Max Act: 2.0154. Min Act: -0.1700
Data Index: 3780250 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9816. Min Act: -0.1700
Data Index: 8304741 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9816. Min Act: -0.1700
Data Index: 6456883 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9986. Min Act: -0.1700
Data Index: 4510383 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9477. Min Act: -0.1700
Data Index: 5635428 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9816. Min Act: -0.1700
Data Index: 1062716 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9647. Min Act: -0.1700
Data Index: 1062710 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9647. Min Act: -0.1700
Data Index: 3524691 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9647. Min Act: -0.1700
Data Index: 5014725 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9307. Min Act: -0.1700
Data Index: 8066 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9477. Min Act: -0.1700
Data Index: 7520451 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9477. Min Act: -0.1700
Data Index: 3190619 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9477. Min Act: -0.1700
Data Index: 5581084 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9307. Min Act: -0.1700
Data Index: 2371358 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1496. Min Range: -2.1496
Max Act: 1.9307. Min Act: -0.1700
Data Index: 7735048 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19