Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.8677. Min Act: -0.1700
Data Index: 998903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.8163. Min Act: -0.1699
Data Index: 2763898 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7818. Min Act: -0.1700
Data Index: 5225115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7732. Min Act: -0.1700
Data Index: 2992166 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7646. Min Act: -0.1700
Data Index: 3267147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7300. Min Act: -0.1700
Data Index: 7629323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7127. Min Act: -0.1700
Data Index: 8578317 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.7214. Min Act: -0.1700
Data Index: 1356797 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6954. Min Act: -0.1700
Data Index: 7592091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6867. Min Act: -0.1700
Data Index: 7016469 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 4966054 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6693. Min Act: -0.1700
Data Index: 8646890 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 8236572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 8376230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 6956228 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 8505818 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 3537833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6780. Min Act: -0.1700
Data Index: 7404049 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6693. Min Act: -0.1700
Data Index: 8492074 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8677. Min Range: -1.8677
Max Act: 1.6607. Min Act: -0.1700
Data Index: 5821109 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19