Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.8596. Min Act: -0.1700
Data Index: 4766556 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.7346. Min Act: -0.1700
Data Index: 6212653 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.4534. Min Act: -0.1700
Data Index: 2812376 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.3909. Min Act: -0.1700
Data Index: 151827 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.3909. Min Act: -0.1700
Data Index: 7165307 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.3596. Min Act: -0.1700
Data Index: 1536092 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.3596. Min Act: -0.1700
Data Index: 4432607 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2659. Min Act: -0.1700
Data Index: 7973251 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2971. Min Act: -0.1700
Data Index: 3163397 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.3284. Min Act: -0.1700
Data Index: 3901879 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2659. Min Act: -0.1700
Data Index: 7249578 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2346. Min Act: -0.1700
Data Index: 7199654 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 6155888 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 1036819 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 2981308 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 2928315 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 6868690 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 2920612 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.2034. Min Act: -0.1700
Data Index: 1169752 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8596. Min Range: -7.8596
Max Act: 7.1721. Min Act: -0.1700
Data Index: 4819582 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19