Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1892 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5289. Min Range: -6.5289
Max Act: 6.5289. Min Act: -0.1700
Data Index: 6245171 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5289. Min Range: -6.5289
Max Act: 6.5289. Min Act: -0.1700
Data Index: 8011944 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5289. Min Range: -6.5289
Max Act: 6.2476. Min Act: -0.1700
Data Index: 3401984 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5289. Min Range: -6.5289
Max Act: 6.1539. Min Act: -0.1700
Data Index: 8011943 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5289. Min Range: -6.5289
Max Act: 6.1539. Min Act: -0.1700
Data Index: 8830694 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.8726. Min Act: -0.1700
Data Index: 701199 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.9039. Min Act: -0.1700
Data Index: 8011945 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.8726. Min Act: -0.1700
Data Index: 4264666 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.8726. Min Act: -0.1700
Data Index: 1862489 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.8101. Min Act: -0.1700
Data Index: 2242288 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.8101. Min Act: -0.1700
Data Index: 8078803 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 8609821 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 211424 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 4120476 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 4353892 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 8473442 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 7824300 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 8668609 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 91169 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5289. Min Range: -6.5289
Max Act: 5.7789. Min Act: -0.1700
Data Index: 7003570 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19