Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.3021. Min Act: -0.1700
Data Index: 3599404 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.2709. Min Act: -0.1700
Data Index: 703921 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.1771. Min Act: -0.1700
Data Index: 4236819 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.1458. Min Act: -0.1700
Data Index: 5732570 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.1146. Min Act: -0.1700
Data Index: 6227328 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 1002302 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 1014500 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0521. Min Act: -0.1700
Data Index: 2010212 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 1099183 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 8161287 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0833. Min Act: -0.1700
Data Index: 6322872 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0521. Min Act: -0.1700
Data Index: 754286 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0521. Min Act: -0.1700
Data Index: 8428243 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0208. Min Act: -0.1700
Data Index: 8428244 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0521. Min Act: -0.1700
Data Index: 2010211 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0208. Min Act: -0.1700
Data Index: 6702171 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0521. Min Act: -0.1700
Data Index: 4702658 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3021. Min Range: -4.3021
Max Act: 3.9895. Min Act: -0.1700
Data Index: 4883316 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0208. Min Act: -0.1700
Data Index: 3982148 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3021. Min Range: -4.3021
Max Act: 4.0208. Min Act: -0.1700
Data Index: 4093767 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19