Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.6811. Min Act: -0.1700
Data Index: 7715754 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.6186. Min Act: -0.1700
Data Index: 4375581 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.5873. Min Act: -0.1700
Data Index: 7502398 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.5248. Min Act: -0.1700
Data Index: 3274352 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.5248. Min Act: -0.1700
Data Index: 7672631 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.4936. Min Act: -0.1700
Data Index: 7175525 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3998. Min Act: -0.1700
Data Index: 3110149 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3686. Min Act: -0.1700
Data Index: 7279181 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3686. Min Act: -0.1700
Data Index: 5339842 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3373. Min Act: -0.1700
Data Index: 5024186 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3686. Min Act: -0.1700
Data Index: 1015040 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.3061. Min Act: -0.1700
Data Index: 1096620 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.2436. Min Act: -0.1700
Data Index: 5767690 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.2436. Min Act: -0.1700
Data Index: 5878717 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.2123. Min Act: -0.1700
Data Index: 3034059 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.2436. Min Act: -0.1700
Data Index: 677346 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.1498. Min Act: -0.1700
Data Index: 3794382 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.1498. Min Act: -0.1700
Data Index: 4520569 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.1811. Min Act: -0.1700
Data Index: 2742018 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6811. Min Range: -7.6811
Max Act: 7.1811. Min Act: -0.1700
Data Index: 4559601 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19