Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.2392. Min Act: -0.1700
Data Index: 2780750 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.2080. Min Act: -0.1700
Data Index: 8089675 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.2080. Min Act: -0.1700
Data Index: 5033890 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0830. Min Act: -0.1700
Data Index: 1288688 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0830. Min Act: -0.1700
Data Index: 8096854 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0517. Min Act: -0.1700
Data Index: 2963459 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0205. Min Act: -0.1700
Data Index: 489910 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0517. Min Act: -0.1700
Data Index: 6970727 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0205. Min Act: -0.1700
Data Index: 3018131 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0205. Min Act: -0.1700
Data Index: 2552577 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2392. Min Range: -5.2392
Max Act: 5.0205. Min Act: -0.1700
Data Index: 5654949 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9892. Min Act: -0.1700
Data Index: 1944858 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9580. Min Act: -0.1700
Data Index: 7209977 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9892. Min Act: -0.1700
Data Index: 6803362 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9892. Min Act: -0.1700
Data Index: 3701741 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9892. Min Act: -0.1700
Data Index: 1071246 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9892. Min Act: -0.1700
Data Index: 4914638 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9267. Min Act: -0.1700
Data Index: 2369680 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9580. Min Act: -0.1700
Data Index: 2772566 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2392. Min Range: -5.2392
Max Act: 4.9267. Min Act: -0.1700
Data Index: 7006027 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19