Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0971. Min Range: -6.0971
Max Act: 6.0971. Min Act: -0.1700
Data Index: 1932187 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.9721. Min Act: -0.1700
Data Index: 7201999 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.9096. Min Act: -0.1700
Data Index: 7532027 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.8471. Min Act: -0.1700
Data Index: 1892730 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.8158. Min Act: -0.1700
Data Index: 7323536 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8476089 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.7533. Min Act: -0.1700
Data Index: 73171 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.7533. Min Act: -0.1700
Data Index: 4709599 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.7533. Min Act: -0.1700
Data Index: 7192802 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6777985 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3130698 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5859785 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5971. Min Act: -0.1700
Data Index: 1663078 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5971. Min Act: -0.1700
Data Index: 3518124 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5658. Min Act: -0.1700
Data Index: 1305925 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5658. Min Act: -0.1700
Data Index: 6430932 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5971. Min Act: -0.1700
Data Index: 4353456 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5346. Min Act: -0.1700
Data Index: 7446193 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5346. Min Act: -0.1700
Data Index: 531577 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0971. Min Range: -6.0971
Max Act: 5.5658. Min Act: -0.1700
Data Index: 5650682 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19