Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1622. Min Range: -7.1622
Max Act: 7.1622. Min Act: -0.1700
Data Index: 6493160 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1622. Min Range: -7.1622
Max Act: 7.1310. Min Act: -0.1700
Data Index: 5659877 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1622. Min Range: -7.1622
Max Act: 7.0060. Min Act: -0.1700
Data Index: 3206801 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.9747. Min Act: -0.1700
Data Index: 5816763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.9435. Min Act: -0.1700
Data Index: 8614417 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.8497. Min Act: -0.1700
Data Index: 1820763 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7872. Min Act: -0.1700
Data Index: 4549747 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.8185. Min Act: -0.1700
Data Index: 192551 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7247. Min Act: -0.1700
Data Index: 290366 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7560. Min Act: -0.1700
Data Index: 4672453 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7560. Min Act: -0.1700
Data Index: 4595935 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7560. Min Act: -0.1700
Data Index: 3852470 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7247. Min Act: -0.1700
Data Index: 4271686 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7247. Min Act: -0.1700
Data Index: 5055264 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.7247. Min Act: -0.1700
Data Index: 2655240 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.6935. Min Act: -0.1700
Data Index: 364878 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.6622. Min Act: -0.1700
Data Index: 7711814 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.6622. Min Act: -0.1700
Data Index: 6972596 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4431003 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1622. Min Range: -7.1622
Max Act: 6.6622. Min Act: -0.1700
Data Index: 141603 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19