Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0900. Min Act: -0.1700
Data Index: 1639003 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0587. Min Act: -0.1700
Data Index: 5615927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0587. Min Act: -0.1700
Data Index: 4925235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0274. Min Act: -0.1700
Data Index: 6689853 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0274. Min Act: -0.1700
Data Index: 2265734 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0274. Min Act: -0.1700
Data Index: 4586215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0900. Min Range: -4.0900
Max Act: 4.0274. Min Act: -0.1700
Data Index: 7099033 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 1024034 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 2865854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 5149602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 8685237 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 6918496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 6890473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 4519058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9962. Min Act: -0.1700
Data Index: 4338480 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9649. Min Act: -0.1699
Data Index: 2635661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9649. Min Act: -0.1700
Data Index: 2956084 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9649. Min Act: -0.1700
Data Index: 5302605 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9649. Min Act: -0.1700
Data Index: 5332736 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0900. Min Range: -4.0900
Max Act: 3.9649. Min Act: -0.1700
Data Index: 3201450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19