Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.2739. Min Act: -0.1700
Data Index: 6979201 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.2427. Min Act: -0.1700
Data Index: 2575765 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.2114. Min Act: -0.1700
Data Index: 531424 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.1802. Min Act: -0.1700
Data Index: 488946 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6278088 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.0864. Min Act: -0.1700
Data Index: 6723254 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.0552. Min Act: -0.1700
Data Index: 5283053 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9927. Min Act: -0.1700
Data Index: 8006922 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9927. Min Act: -0.1700
Data Index: 411895 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9927. Min Act: -0.1700
Data Index: 4484503 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2739. Min Range: -5.2739
Max Act: 5.0239. Min Act: -0.1700
Data Index: 1431638 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9302. Min Act: -0.1700
Data Index: 369492 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1635726 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9302. Min Act: -0.1700
Data Index: 551522 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.9302. Min Act: -0.1700
Data Index: 7643667 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8989. Min Act: -0.1700
Data Index: 5204530 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8989. Min Act: -0.1700
Data Index: 83740 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8677. Min Act: -0.1700
Data Index: 7084928 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8364. Min Act: -0.1700
Data Index: 7893977 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2739. Min Range: -5.2739
Max Act: 4.8989. Min Act: -0.1700
Data Index: 5801716 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19