Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2466. Min Range: -7.2466
Max Act: 7.2466. Min Act: -0.1700
Data Index: 6051984 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.9966. Min Act: -0.1700
Data Index: 83757 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.9654. Min Act: -0.1700
Data Index: 8085277 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.9029. Min Act: -0.1700
Data Index: 7499722 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.8404. Min Act: -0.1700
Data Index: 3928208 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.8404. Min Act: -0.1700
Data Index: 6957516 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.8091. Min Act: -0.1700
Data Index: 2683382 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7779. Min Act: -0.1700
Data Index: 8706549 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7779. Min Act: -0.1700
Data Index: 6223466 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7779. Min Act: -0.1700
Data Index: 2461928 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7779. Min Act: -0.1700
Data Index: 7967382 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7779. Min Act: -0.1700
Data Index: 7578705 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7466. Min Act: -0.1700
Data Index: 456860 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7154. Min Act: -0.1700
Data Index: 298059 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7154. Min Act: -0.1700
Data Index: 8399309 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7154. Min Act: -0.1700
Data Index: 2992275 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7154. Min Act: -0.1700
Data Index: 261626 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.7154. Min Act: -0.1700
Data Index: 3470695 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.6841. Min Act: -0.1700
Data Index: 1748805 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2466. Min Range: -7.2466
Max Act: 6.6841. Min Act: -0.1700
Data Index: 2670906 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19