Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0794. Min Range: -7.0794
Max Act: 7.0794. Min Act: -0.1700
Data Index: 7181323 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0794. Min Range: -7.0794
Max Act: 7.0169. Min Act: -0.1700
Data Index: 4100313 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.9231. Min Act: -0.1700
Data Index: 6955871 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.8919. Min Act: -0.1700
Data Index: 2427504 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.8919. Min Act: -0.1700
Data Index: 1972391 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.7669. Min Act: -0.1700
Data Index: 6340454 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.7356. Min Act: -0.1700
Data Index: 1500098 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6731. Min Act: -0.1700
Data Index: 4804733 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6731. Min Act: -0.1700
Data Index: 3189240 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6419. Min Act: -0.1700
Data Index: 1348963 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6419. Min Act: -0.1700
Data Index: 2180932 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6106. Min Act: -0.1700
Data Index: 327457 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6106. Min Act: -0.1700
Data Index: 2514685 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6106. Min Act: -0.1700
Data Index: 4303658 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6106. Min Act: -0.1700
Data Index: 6770450 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.5481. Min Act: -0.1700
Data Index: 4201966 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.6106. Min Act: -0.1700
Data Index: 7004304 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.5794. Min Act: -0.1700
Data Index: 1674122 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.5794. Min Act: -0.1700
Data Index: 6827416 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0794. Min Range: -7.0794
Max Act: 6.5481. Min Act: -0.1700
Data Index: 4930155 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19