Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.7726. Min Act: -0.1700
Data Index: 4438071 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.7101. Min Act: -0.1700
Data Index: 4332076 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.6476. Min Act: -0.1700
Data Index: 3848873 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.5851. Min Act: -0.1700
Data Index: 4973916 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.5851. Min Act: -0.1700
Data Index: 8140508 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.5539. Min Act: -0.1700
Data Index: 841376 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.5226. Min Act: -0.1700
Data Index: 846006 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.4601. Min Act: -0.1700
Data Index: 1730894 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.4601. Min Act: -0.1700
Data Index: 6735825 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.3976. Min Act: -0.1700
Data Index: 5915696 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.3664. Min Act: -0.1700
Data Index: 8314133 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.3039. Min Act: -0.1700
Data Index: 1056651 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.3039. Min Act: -0.1700
Data Index: 6569026 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.2414. Min Act: -0.1700
Data Index: 720114 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.2726. Min Act: -0.1700
Data Index: 160336 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.2414. Min Act: -0.1700
Data Index: 1953861 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.1789. Min Act: -0.1700
Data Index: 2160854 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.1789. Min Act: -0.1700
Data Index: 904734 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.2101. Min Act: -0.1700
Data Index: 1902981 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7726. Min Range: -5.7726
Max Act: 5.1789. Min Act: -0.1700
Data Index: 2103390 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19