Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5540. Min Range: -8.5540
Max Act: 8.4915. Min Act: -0.1700
Data Index: 357969 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5540. Min Range: -8.5540
Max Act: 8.5540. Min Act: -0.1700
Data Index: 5157366 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5540. Min Range: -8.5540
Max Act: 8.1790. Min Act: -0.1700
Data Index: 6016579 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5540. Min Range: -8.5540
Max Act: 8.1790. Min Act: -0.1700
Data Index: 4226377 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.9290. Min Act: -0.1700
Data Index: 5936050 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.8665. Min Act: -0.1700
Data Index: 1962318 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.8040. Min Act: -0.1700
Data Index: 529082 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.7727. Min Act: -0.1700
Data Index: 4225755 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.7102. Min Act: -0.1700
Data Index: 3694588 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6790. Min Act: -0.1700
Data Index: 5043478 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.7102. Min Act: -0.1700
Data Index: 7800110 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6790. Min Act: -0.1700
Data Index: 7706673 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6790. Min Act: -0.1700
Data Index: 387315 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6477. Min Act: -0.1700
Data Index: 3568703 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6790. Min Act: -0.1700
Data Index: 7815486 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6477. Min Act: -0.1700
Data Index: 3388944 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.6165. Min Act: -0.1700
Data Index: 5043475 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.5540. Min Act: -0.1700
Data Index: 4587109 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.5852. Min Act: -0.1700
Data Index: 799560 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5540. Min Range: -8.5540
Max Act: 7.5540. Min Act: -0.1700
Data Index: 7579975 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19