Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7986. Min Act: -0.1700
Data Index: 8047728 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7674. Min Act: -0.1700
Data Index: 2450724 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7361. Min Act: -0.1700
Data Index: 4670859 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.7049. Min Act: -0.1700
Data Index: 2450723 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.6111. Min Act: -0.1700
Data Index: 2450727 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5799. Min Act: -0.1700
Data Index: 4801562 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5486. Min Act: -0.1700
Data Index: 5563278 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5486. Min Act: -0.1700
Data Index: 5376716 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.5174. Min Act: -0.1700
Data Index: 1795568 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.4549. Min Act: -0.1700
Data Index: 4760099 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.4236. Min Act: -0.1700
Data Index: 3025405 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.3924. Min Act: -0.1700
Data Index: 2695641 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.3924. Min Act: -0.1700
Data Index: 5813127 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.3611. Min Act: -0.1700
Data Index: 4741471 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.3299. Min Act: -0.1700
Data Index: 5642392 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.2986. Min Act: -0.1700
Data Index: 5127420 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.2674. Min Act: -0.1700
Data Index: 7289312 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.2986. Min Act: -0.1700
Data Index: 1736159 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.2674. Min Act: -0.1700
Data Index: 4741468 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7986. Min Range: -4.7986
Max Act: 4.2674. Min Act: -0.1700
Data Index: 3199581 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19