Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.6482. Min Act: -0.1700
Data Index: 4607325 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.6012. Min Act: -0.1700
Data Index: 8454375 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5699. Min Act: -0.1700
Data Index: 4613274 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7307145 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7373344 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5543. Min Act: -0.1700
Data Index: 3765669 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5543. Min Act: -0.1700
Data Index: 3901226 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5543. Min Act: -0.1700
Data Index: 8200726 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 3029605 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 2839943 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5230. Min Act: -0.1700
Data Index: 6254189 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5997701 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 684972 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 4262133 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5870112 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5323116 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5230. Min Act: -0.1700
Data Index: 4741234 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5230. Min Act: -0.1700
Data Index: 1682002 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5230. Min Act: -0.1700
Data Index: 5040610 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6482. Min Range: -3.6482
Max Act: 3.5386. Min Act: -0.1700
Data Index: 6999097 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19