Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3572. Min Range: -9.3572
Max Act: 9.3572. Min Act: -0.1700
Data Index: 1708620 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3572. Min Range: -9.3572
Max Act: 9.2322. Min Act: -0.1700
Data Index: 6329077 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3572. Min Range: -9.3572
Max Act: 9.1072. Min Act: -0.1700
Data Index: 6023688 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.9822. Min Act: -0.1700
Data Index: 1356687 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.9822. Min Act: -0.1700
Data Index: 7961793 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7947. Min Act: -0.1700
Data Index: 1167443 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7947. Min Act: -0.1700
Data Index: 4241738 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.8572. Min Act: -0.1700
Data Index: 2525943 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7947. Min Act: -0.1700
Data Index: 3323159 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 1075684 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 4043321 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 7402794 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 1153198 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 8322606 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 4602788 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.6697. Min Act: -0.1700
Data Index: 2067291 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.6697. Min Act: -0.1700
Data Index: 4694960 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.7322. Min Act: -0.1700
Data Index: 7742480 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.6697. Min Act: -0.1700
Data Index: 6012102 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3572. Min Range: -9.3572
Max Act: 8.6697. Min Act: -0.1700
Data Index: 2637102 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19