Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.5528. Min Act: -0.1700
Data Index: 7804884 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.5215. Min Act: -0.1700
Data Index: 1719981 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 3603349 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 8747052 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 2868535 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 5181762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 3628865 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4902. Min Act: -0.1700
Data Index: 1224693 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 2570463 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 6393683 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 6636495 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 464570 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 4836351 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 1372589 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 7496598 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 1166849 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 2149099 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 1195167 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4588. Min Act: -0.1700
Data Index: 3318959 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5528. Min Range: -3.5528
Max Act: 3.4275. Min Act: -0.1700
Data Index: 3137260 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19