Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.7019. Min Act: -0.1700
Data Index: 5283681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.7019. Min Act: -0.1700
Data Index: 6658795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6707. Min Act: -0.1700
Data Index: 8676574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6707. Min Act: -0.1700
Data Index: 7353426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6707. Min Act: -0.1700
Data Index: 3469434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 3823610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 3369452 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 7946592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 8455274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 8759632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6394. Min Act: -0.1700
Data Index: 4939336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 4038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 1325020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 3263167 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2435334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.5769. Min Act: -0.1700
Data Index: 454385 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 839105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 2063617 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 810353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7019. Min Range: -4.7019
Max Act: 4.6082. Min Act: -0.1700
Data Index: 3206923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19