Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1033 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.7321. Min Act: -0.1700
Data Index: 1670483 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.5758. Min Act: -0.1700
Data Index: 850800 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.5446. Min Act: -0.1700
Data Index: 1138567 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.5133. Min Act: -0.1700
Data Index: 373925 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4821. Min Act: -0.1700
Data Index: 8437032 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4196. Min Act: -0.1700
Data Index: 3508642 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.4196. Min Act: -0.1700
Data Index: 3295645 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3883. Min Act: -0.1700
Data Index: 6855102 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3571. Min Act: -0.1700
Data Index: 5100306 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.3258. Min Act: -0.1700
Data Index: 6748369 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2946. Min Act: -0.1700
Data Index: 6804031 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2946. Min Act: -0.1700
Data Index: 2383012 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2946. Min Act: -0.1700
Data Index: 2368811 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2633. Min Act: -0.1700
Data Index: 2415231 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 2313048 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 2755101 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2008. Min Act: -0.1700
Data Index: 8092241 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2321. Min Act: -0.1700
Data Index: 719114 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.2008. Min Act: -0.1700
Data Index: 2681732 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7321. Min Range: -7.7321
Max Act: 7.1383. Min Act: -0.1700
Data Index: 3624106 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19