Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4705 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.9311. Min Act: -0.1700
Data Index: 3960128 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.6811. Min Act: -0.1698
Data Index: 8033009 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.6811. Min Act: -0.1700
Data Index: 8291688 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.6186. Min Act: -0.1700
Data Index: 8154474 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.6186. Min Act: -0.1700
Data Index: 2596412 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.4936. Min Act: -0.1700
Data Index: 1640714 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.4311. Min Act: -0.1700
Data Index: 5361897 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.2748. Min Act: -0.1700
Data Index: 3976430 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.2748. Min Act: -0.1700
Data Index: 3430516 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1811. Min Act: -0.1700
Data Index: 2256455 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1498. Min Act: -0.1700
Data Index: 1811583 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1498. Min Act: -0.1700
Data Index: 6607437 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1498. Min Act: -0.1700
Data Index: 2869392 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1186. Min Act: -0.1700
Data Index: 4275064 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1186. Min Act: -0.1700
Data Index: 2498767 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1186. Min Act: -0.1700
Data Index: 5269804 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1186. Min Act: -0.1700
Data Index: 4781426 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.1186. Min Act: -0.1700
Data Index: 7915810 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.0561. Min Act: -0.1700
Data Index: 4682685 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9311. Min Range: -8.9311
Max Act: 8.0561. Min Act: -0.1700
Data Index: 5021065 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19