Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2828. Min Range: -8.2828
Max Act: 8.2828. Min Act: -0.1700
Data Index: 1106407 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2828. Min Range: -8.2828
Max Act: 8.2203. Min Act: -0.1700
Data Index: 160622 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.9703. Min Act: -0.1700
Data Index: 1918978 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.9703. Min Act: -0.1700
Data Index: 4422889 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.9078. Min Act: -0.1700
Data Index: 4272966 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.9078. Min Act: -0.1700
Data Index: 7404730 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.7828. Min Act: -0.1700
Data Index: 6941963 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.8453. Min Act: -0.1700
Data Index: 8346636 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.8453. Min Act: -0.1700
Data Index: 3382879 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.7828. Min Act: -0.1700
Data Index: 8743414 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.8453. Min Act: -0.1700
Data Index: 5634130 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.7828. Min Act: -0.1700
Data Index: 2413778 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.7828. Min Act: -0.1700
Data Index: 7192004 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.7203. Min Act: -0.1700
Data Index: 4577471 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.6578. Min Act: -0.1700
Data Index: 1188170 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.6578. Min Act: -0.1700
Data Index: 1359197 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.6578. Min Act: -0.1700
Data Index: 2425954 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.6578. Min Act: -0.1700
Data Index: 990335 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.5953. Min Act: -0.1700
Data Index: 7207238 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2828. Min Range: -8.2828
Max Act: 7.5328. Min Act: -0.1700
Data Index: 1537237 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19