Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1164. Min Range: -6.1164
Max Act: 6.1164. Min Act: -0.1700
Data Index: 1139123 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1164. Min Range: -6.1164
Max Act: 6.1164. Min Act: -0.1700
Data Index: 5820881 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9914. Min Act: -0.1700
Data Index: 7263770 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 216028 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 6676480 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9602. Min Act: -0.1700
Data Index: 8043651 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 5822113 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 8272345 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8977. Min Act: -0.1700
Data Index: 191646 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8977. Min Act: -0.1700
Data Index: 1254094 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.9289. Min Act: -0.1700
Data Index: 4491754 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8977. Min Act: -0.1700
Data Index: 124321 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8664. Min Act: -0.1700
Data Index: 13331 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8039. Min Act: -0.1700
Data Index: 3213793 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8352. Min Act: -0.1700
Data Index: 5377825 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8352. Min Act: -0.1700
Data Index: 6256272 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3248098 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.8039. Min Act: -0.1700
Data Index: 5711307 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.7414. Min Act: -0.1700
Data Index: 4139631 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1164. Min Range: -6.1164
Max Act: 5.7414. Min Act: -0.1700
Data Index: 5401060 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19