Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0704. Min Range: -3.0704
Max Act: 3.0704. Min Act: -0.1700
Data Index: 8426787 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.9123. Min Act: -0.1700
Data Index: 4554263 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8806. Min Act: -0.1700
Data Index: 1359251 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8647. Min Act: -0.1700
Data Index: 4649156 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8170. Min Act: -0.1700
Data Index: 8261266 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8170. Min Act: -0.1700
Data Index: 6121773 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8011. Min Act: -0.1700
Data Index: 8756400 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7852. Min Act: -0.1700
Data Index: 3637163 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.8011. Min Act: -0.1700
Data Index: 6138924 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7852. Min Act: -0.1700
Data Index: 8756399 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7852. Min Act: -0.1700
Data Index: 2766359 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7692. Min Act: -0.1700
Data Index: 2714769 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7373. Min Act: -0.1700
Data Index: 4806454 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7692. Min Act: -0.1700
Data Index: 2898354 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7533. Min Act: -0.1700
Data Index: 1381669 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7373. Min Act: -0.1700
Data Index: 7258869 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7213. Min Act: -0.1700
Data Index: 7258871 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7213. Min Act: -0.1700
Data Index: 1359249 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7213. Min Act: -0.1700
Data Index: 7258868 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0704. Min Range: -3.0704
Max Act: 2.7213. Min Act: -0.1700
Data Index: 2766360 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19