Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0723. Min Range: -7.0723
Max Act: 7.0723. Min Act: -0.1700
Data Index: 7286738 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0723. Min Range: -7.0723
Max Act: 7.0098. Min Act: -0.1700
Data Index: 6851936 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.9473. Min Act: -0.1700
Data Index: 7784361 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.9161. Min Act: -0.1700
Data Index: 5857846 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.8848. Min Act: -0.1700
Data Index: 8568419 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.8536. Min Act: -0.1700
Data Index: 2244856 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.8223. Min Act: -0.1700
Data Index: 1706060 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.8223. Min Act: -0.1700
Data Index: 3573498 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7911. Min Act: -0.1700
Data Index: 4459769 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7911. Min Act: -0.1700
Data Index: 6070265 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7598. Min Act: -0.1700
Data Index: 7574642 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7286. Min Act: -0.1700
Data Index: 7720381 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7598. Min Act: -0.1700
Data Index: 3447395 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7598. Min Act: -0.1700
Data Index: 2098876 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7911. Min Act: -0.1700
Data Index: 3108537 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7598. Min Act: -0.1700
Data Index: 3530022 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7598. Min Act: -0.1700
Data Index: 7784360 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.6973. Min Act: -0.1700
Data Index: 3573494 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7286. Min Act: -0.1700
Data Index: 5946386 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0723. Min Range: -7.0723
Max Act: 6.7286. Min Act: -0.1700
Data Index: 2164021 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19