Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.2748. Min Act: -0.1700
Data Index: 1386353 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.2748. Min Act: -0.1700
Data Index: 3676520 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.1498. Min Act: -0.1700
Data Index: 5937963 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 6189009 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 6918352 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 235852 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 8452961 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 4839494 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2748. Min Range: -4.2748
Max Act: 4.0247. Min Act: -0.1700
Data Index: 1782848 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9622. Min Act: -0.1700
Data Index: 4681351 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9622. Min Act: -0.1700
Data Index: 2439293 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 8494971 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 1335536 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 5057844 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 4849228 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9622. Min Act: -0.1700
Data Index: 2016093 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 3257291 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 602471 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.9309. Min Act: -0.1700
Data Index: 733648 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2748. Min Range: -4.2748
Max Act: 3.8997. Min Act: -0.1700
Data Index: 2412000 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19