Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1209 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3725. Min Act: -0.1700
Data Index: 6902802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 4138565 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 3426066 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 4571080 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 3314099 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 3876743 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 932710 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 3675809 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 1947482 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 908595 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 4002596 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 4950276 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 2389935 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 772839 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 1449690 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 1885491 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 1396651 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 4899762 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 1649562 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3725. Min Range: -3.3725
Max Act: 3.3411. Min Act: -0.1700
Data Index: 3918305 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19