Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.9347. Min Act: -0.1700
Data Index: 3033820 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.7160. Min Act: -0.1700
Data Index: 6007149 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.5910. Min Act: -0.1700
Data Index: 5961984 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.4660. Min Act: -0.1700
Data Index: 6577299 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.4035. Min Act: -0.1700
Data Index: 7983525 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.3097. Min Act: -0.1700
Data Index: 8433578 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.2472. Min Act: -0.1700
Data Index: 8207159 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.2785. Min Act: -0.1700
Data Index: 7193152 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.2472. Min Act: -0.1700
Data Index: 4735177 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.2472. Min Act: -0.1700
Data Index: 7760036 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.2160. Min Act: -0.1700
Data Index: 6359244 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.1535. Min Act: -0.1700
Data Index: 8122689 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.1535. Min Act: -0.1700
Data Index: 7279782 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.1222. Min Act: -0.1700
Data Index: 2979531 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.0597. Min Act: -0.1700
Data Index: 6122326 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.0597. Min Act: -0.1700
Data Index: 6212334 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.0285. Min Act: -0.1700
Data Index: 5655783 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9347. Min Range: -7.9347
Max Act: 6.9972. Min Act: -0.1700
Data Index: 3384621 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9347. Min Range: -7.9347
Max Act: 7.0285. Min Act: -0.1700
Data Index: 3374128 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9347. Min Range: -7.9347
Max Act: 6.9660. Min Act: -0.1700
Data Index: 5100648 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19