Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.7361. Min Act: -0.1700
Data Index: 3290483 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.6111. Min Act: -0.1700
Data Index: 635491 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.6111. Min Act: -0.1700
Data Index: 1441558 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5799. Min Act: -0.1700
Data Index: 8590647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4293845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5799. Min Act: -0.1700
Data Index: 2116670 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5486. Min Act: -0.1698
Data Index: 3058675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5486. Min Act: -0.1700
Data Index: 1540425 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5486. Min Act: -0.1700
Data Index: 469872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5486. Min Act: -0.1700
Data Index: 6500375 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5486. Min Act: -0.1700
Data Index: 2700857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5174. Min Act: -0.1700
Data Index: 4691730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5174. Min Act: -0.1700
Data Index: 1896882 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5174. Min Act: -0.1700
Data Index: 6011944 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5174. Min Act: -0.1700
Data Index: 5319326 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.4861. Min Act: -0.1700
Data Index: 2175711 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.4861. Min Act: -0.1700
Data Index: 388190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.5174. Min Act: -0.1700
Data Index: 1247257 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.4861. Min Act: -0.1700
Data Index: 2931605 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7361. Min Range: -5.7361
Max Act: 5.4861. Min Act: -0.1700
Data Index: 364055 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19