Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1245 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1126. Min Range: -7.1126
Max Act: 7.1126. Min Act: -0.1700
Data Index: 3047853 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1126. Min Range: -7.1126
Max Act: 7.0501. Min Act: -0.1700
Data Index: 3732022 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1126. Min Range: -7.1126
Max Act: 7.0189. Min Act: -0.1700
Data Index: 8753232 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.8939. Min Act: -0.1700
Data Index: 5673412 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.8314. Min Act: -0.1700
Data Index: 8603975 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.8314. Min Act: -0.1700
Data Index: 7892127 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.7689. Min Act: -0.1700
Data Index: 6598381 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.7689. Min Act: -0.1700
Data Index: 4249949 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.7064. Min Act: -0.1700
Data Index: 2112602 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6751. Min Act: -0.1700
Data Index: 5205892 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6751. Min Act: -0.1700
Data Index: 3461661 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5173245 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 343725 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 2302310 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.6126. Min Act: -0.1700
Data Index: 3519501 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5814. Min Act: -0.1700
Data Index: 7699032 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5814. Min Act: -0.1700
Data Index: 3564697 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5189. Min Act: -0.1700
Data Index: 4543486 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 5052777 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1126. Min Range: -7.1126
Max Act: 6.5501. Min Act: -0.1700
Data Index: 3922461 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19