Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.4333. Min Act: -0.1699
Data Index: 5737972 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.4333. Min Act: -0.1700
Data Index: 2616893 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.4021. Min Act: -0.1700
Data Index: 1834091 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3708. Min Act: -0.1700
Data Index: 6261286 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3708. Min Act: -0.1700
Data Index: 2629765 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3708. Min Act: -0.1700
Data Index: 3039921 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3396. Min Act: -0.1700
Data Index: 2886104 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3396. Min Act: -0.1700
Data Index: 4510568 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 544838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 26929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 5727002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 5017099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 3197674 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 2150766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 1266568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 1227979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 3035196 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 743148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 1349826 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4333. Min Range: -4.4333
Max Act: 4.3083. Min Act: -0.1700
Data Index: 4300733 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19