Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3936. Min Range: -10.3936
Max Act: 10.3936. Min Act: -0.1700
Data Index: 5339118 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3936. Min Range: -10.3936
Max Act: 10.0186. Min Act: -0.1700
Data Index: 1694020 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.9561. Min Act: -0.1700
Data Index: 3869296 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.8311. Min Act: -0.1700
Data Index: 8435350 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.8311. Min Act: -0.1700
Data Index: 6162278 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.7686. Min Act: -0.1700
Data Index: 3163505 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.6436. Min Act: -0.1700
Data Index: 3208484 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.5811. Min Act: -0.1700
Data Index: 3090998 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.5811. Min Act: -0.1700
Data Index: 6644220 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.5186. Min Act: -0.1700
Data Index: 7373390 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.4561. Min Act: -0.1700
Data Index: 4411634 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.4561. Min Act: -0.1700
Data Index: 3529481 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.3936. Min Act: -0.1700
Data Index: 2456123 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.4561. Min Act: -0.1700
Data Index: 3723340 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.3311. Min Act: -0.1700
Data Index: 2672309 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.3311. Min Act: -0.1700
Data Index: 8137022 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.2686. Min Act: -0.1700
Data Index: 7107609 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.2686. Min Act: -0.1700
Data Index: 6374281 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.2686. Min Act: -0.1700
Data Index: 1829370 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3936. Min Range: -10.3936
Max Act: 9.2061. Min Act: -0.1700
Data Index: 5582662 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19