Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2208. Min Range: -7.2208
Max Act: 7.1895. Min Act: -0.1700
Data Index: 2632865 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2208. Min Range: -7.2208
Max Act: 7.2208. Min Act: -0.1700
Data Index: 4846501 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.9083. Min Act: -0.1700
Data Index: 1399075 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.8770. Min Act: -0.1700
Data Index: 7098215 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.8458. Min Act: -0.1700
Data Index: 4055224 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7964769 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.6895. Min Act: -0.1700
Data Index: 6115234 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.6583. Min Act: -0.1700
Data Index: 5499838 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.6583. Min Act: -0.1700
Data Index: 5398266 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.6270. Min Act: -0.1700
Data Index: 4792425 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.5958. Min Act: -0.1700
Data Index: 5842028 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.5333. Min Act: -0.1700
Data Index: 3380041 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.5333. Min Act: -0.1700
Data Index: 1175980 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.5020. Min Act: -0.1700
Data Index: 3088523 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4708. Min Act: -0.1700
Data Index: 1269125 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4083. Min Act: -0.1700
Data Index: 3094257 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4395. Min Act: -0.1700
Data Index: 5806000 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4395. Min Act: -0.1700
Data Index: 959852 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4083. Min Act: -0.1700
Data Index: 5448911 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2208. Min Range: -7.2208
Max Act: 6.4083. Min Act: -0.1700
Data Index: 854054 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19