Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.4321. Min Act: -0.1700
Data Index: 6744451 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2446. Min Act: -0.1700
Data Index: 1247487 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2758. Min Act: -0.1700
Data Index: 6125073 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.2133. Min Act: -0.1700
Data Index: 5595701 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.1508. Min Act: -0.1700
Data Index: 3964699 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.1508. Min Act: -0.1700
Data Index: 4322231 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.1196. Min Act: -0.1700
Data Index: 4577977 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.1196. Min Act: -0.1700
Data Index: 575797 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4321. Min Range: -4.4321
Max Act: 4.0258. Min Act: -0.1700
Data Index: 4041292 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6425863 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 3121957 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 2633361 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 65870 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9320. Min Act: -0.1700
Data Index: 1203675 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 5048841 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9945. Min Act: -0.1700
Data Index: 5332614 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 3724133 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9320. Min Act: -0.1700
Data Index: 2911273 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9320. Min Act: -0.1700
Data Index: 2146822 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4321. Min Range: -4.4321
Max Act: 3.9633. Min Act: -0.1700
Data Index: 4741062 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19