Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4159 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2096. Min Range: -6.2096
Max Act: 6.2096. Min Act: -0.1700
Data Index: 907867 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.5846. Min Act: -0.1700
Data Index: 6829641 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.5534. Min Act: -0.1700
Data Index: 7898544 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.3971. Min Act: -0.1700
Data Index: 5218345 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.2409. Min Act: -0.1700
Data Index: 2918811 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.2096. Min Act: -0.1700
Data Index: 3643677 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.1471. Min Act: -0.1700
Data Index: 4279219 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.1471. Min Act: -0.1700
Data Index: 2919699 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.1159. Min Act: -0.1700
Data Index: 3979781 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6434209 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2096. Min Range: -6.2096
Max Act: 5.0221. Min Act: -0.1700
Data Index: 2813381 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9909. Min Act: -0.1700
Data Index: 8442439 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9909. Min Act: -0.1700
Data Index: 6434213 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9909. Min Act: -0.1700
Data Index: 4503508 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9284. Min Act: -0.1700
Data Index: 4928678 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.8971. Min Act: -0.1700
Data Index: 3916472 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.8971. Min Act: -0.1700
Data Index: 1543657 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9284. Min Act: -0.1700
Data Index: 8464706 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.9284. Min Act: -0.1700
Data Index: 3979138 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2096. Min Range: -6.2096
Max Act: 4.8971. Min Act: -0.1700
Data Index: 4248905 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19