Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.8031. Min Act: -0.1700
Data Index: 8233621 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.7562. Min Act: -0.1700
Data Index: 2679527 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.7249. Min Act: -0.1700
Data Index: 6085036 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.6623. Min Act: -0.1700
Data Index: 8671862 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.6779. Min Act: -0.1700
Data Index: 5224864 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.6623. Min Act: -0.1700
Data Index: 4824852 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5997. Min Act: -0.1700
Data Index: 4348389 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.6154. Min Act: -0.1700
Data Index: 1130425 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5997. Min Act: -0.1700
Data Index: 3173674 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5997. Min Act: -0.1700
Data Index: 6152201 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5841. Min Act: -0.1700
Data Index: 5836276 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5997. Min Act: -0.1700
Data Index: 2484330 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5997. Min Act: -0.1700
Data Index: 8213345 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5527. Min Act: -0.1700
Data Index: 673942 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5527. Min Act: -0.1700
Data Index: 7332174 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5371. Min Act: -0.1700
Data Index: 2880152 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5527. Min Act: -0.1700
Data Index: 308879 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5684. Min Act: -0.1700
Data Index: 4736497 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5214. Min Act: -0.1700
Data Index: 8125154 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8031. Min Range: -3.8031
Max Act: 3.5371. Min Act: -0.1700
Data Index: 4826290 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19