Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5181 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.9631. Min Act: -0.1700
Data Index: 5313434 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.7443. Min Act: -0.1700
Data Index: 7607228 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.7443. Min Act: -0.1700
Data Index: 4095564 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.7130. Min Act: -0.1700
Data Index: 6084943 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.7443. Min Act: -0.1700
Data Index: 3543131 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1281697 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1038612 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6817. Min Act: -0.1700
Data Index: 6258504 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6817. Min Act: -0.1700
Data Index: 395940 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.7130. Min Act: -0.1700
Data Index: 6258505 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6504. Min Act: -0.1700
Data Index: 3152327 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6504. Min Act: -0.1700
Data Index: 5135534 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6347. Min Act: -0.1700
Data Index: 7719322 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6034. Min Act: -0.1700
Data Index: 4498041 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6191. Min Act: -0.1700
Data Index: 1969864 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6191. Min Act: -0.1700
Data Index: 4449556 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6034. Min Act: -0.1700
Data Index: 1397630 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6034. Min Act: -0.1700
Data Index: 4827936 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.6034. Min Act: -0.1700
Data Index: 8151252 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9631. Min Range: -3.9631
Max Act: 3.5878. Min Act: -0.1700
Data Index: 2374010 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19