Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.3395. Min Act: -0.1700
Data Index: 6855473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2458. Min Act: -0.1700
Data Index: 5828225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2458. Min Act: -0.1700
Data Index: 8818376 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2458. Min Act: -0.1700
Data Index: 286337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 1133818 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.2145. Min Act: -0.1700
Data Index: 2666449 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1833. Min Act: -0.1700
Data Index: 4878682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1833. Min Act: -0.1700
Data Index: 1266661 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 3027686 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 2062062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 3410927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 2959404 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 2024633 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 2605759 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 1074221 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 1538377 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 2520542 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 1475745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 857452 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3395. Min Range: -4.3395
Max Act: 4.1520. Min Act: -0.1700
Data Index: 1660859 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19