Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 376 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2738. Min Range: -6.2738
Max Act: 6.2738. Min Act: -0.1700
Data Index: 2172599 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2738. Min Range: -6.2738
Max Act: 6.0238. Min Act: -0.1700
Data Index: 5640573 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4661346 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9301. Min Act: -0.1700
Data Index: 6421997 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7437486 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7338568 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3168445 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9301. Min Act: -0.1700
Data Index: 6020964 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.9301. Min Act: -0.1700
Data Index: 2606350 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8988. Min Act: -0.1700
Data Index: 7823943 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 7215849 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 2008426 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 6174536 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 3976951 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 2375948 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8988. Min Act: -0.1700
Data Index: 8682495 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8676. Min Act: -0.1700
Data Index: 1331395 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8363. Min Act: -0.1700
Data Index: 2549111 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8363. Min Act: -0.1700
Data Index: 6749884 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2738. Min Range: -6.2738
Max Act: 5.8363. Min Act: -0.1700
Data Index: 8244091 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19