Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 191 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.2778. Min Act: -0.1697
Data Index: 2971649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3135024 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0903. Min Act: -0.1700
Data Index: 2955063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0903. Min Act: -0.1700
Data Index: 5622737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0903. Min Act: -0.1700
Data Index: 4517901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0590. Min Act: -0.1700
Data Index: 3069950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 4882431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 4872456 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 3995961 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 67546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 1609293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 911537 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 5813741 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1699
Data Index: 571285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 5467133 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1682
Data Index: 1328985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3771268 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9653. Min Act: -0.1700
Data Index: 3510963 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2778. Min Range: -5.2778
Max Act: 4.9965. Min Act: -0.1699
Data Index: 5685511 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2778. Min Range: -5.2778
Max Act: 5.0278. Min Act: -0.1700
Data Index: 5080431 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19