Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.4200. Min Act: -0.1700
Data Index: 6384631 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.4200. Min Act: -0.1700
Data Index: 4807223 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3888. Min Act: -0.1700
Data Index: 5059874 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3888. Min Act: -0.1700
Data Index: 8710348 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3575. Min Act: -0.1700
Data Index: 4738116 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3263. Min Act: -0.1700
Data Index: 8053795 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3263. Min Act: -0.1700
Data Index: 1144286 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2950. Min Act: -0.1700
Data Index: 4271006 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3263. Min Act: -0.1700
Data Index: 4214269 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.3263. Min Act: -0.1700
Data Index: 3091497 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2950. Min Act: -0.1700
Data Index: 4299583 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2950. Min Act: -0.1700
Data Index: 5439363 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 7474574 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 3528150 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 4713770 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 4686165 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2638. Min Act: -0.1700
Data Index: 956792 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2013. Min Act: -0.1700
Data Index: 5574886 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2325. Min Act: -0.1700
Data Index: 2139858 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4200. Min Range: -5.4200
Max Act: 5.2325. Min Act: -0.1700
Data Index: 108166 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19