Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3856 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.3120. Min Act: -0.1700
Data Index: 5367524 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2806. Min Act: -0.1700
Data Index: 93533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2806. Min Act: -0.1700
Data Index: 7467314 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3368169 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2806. Min Act: -0.1700
Data Index: 424674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2806. Min Act: -0.1700
Data Index: 6876485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 176925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 1653388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 3364722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 403672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 2842773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 546805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 4114528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 976087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 1715032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 1002548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 1826847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 4817906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 5311972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3120. Min Range: -3.3120
Max Act: 3.2492. Min Act: -0.1700
Data Index: 1867069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19