Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0086. Min Range: -5.0086
Max Act: 5.0086. Min Act: -0.1700
Data Index: 120302 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0086. Min Range: -5.0086
Max Act: 5.0086. Min Act: -0.1700
Data Index: 3282089 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.9149. Min Act: -0.1700
Data Index: 4939285 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.9461. Min Act: -0.1700
Data Index: 5054188 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8836. Min Act: -0.1700
Data Index: 7617032 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8836. Min Act: -0.1700
Data Index: 8502842 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3466354 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8836. Min Act: -0.1700
Data Index: 7929739 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8836. Min Act: -0.1700
Data Index: 3037659 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8211. Min Act: -0.1700
Data Index: 454464 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8211. Min Act: -0.1700
Data Index: 6777554 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7899. Min Act: -0.1700
Data Index: 8636542 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.8211. Min Act: -0.1700
Data Index: 3635479 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7899. Min Act: -0.1700
Data Index: 4605451 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7899. Min Act: -0.1700
Data Index: 6777577 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7274. Min Act: -0.1700
Data Index: 7929745 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7274. Min Act: -0.1700
Data Index: 5017395 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7274. Min Act: -0.1700
Data Index: 3222677 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.6961. Min Act: -0.1700
Data Index: 5553810 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0086. Min Range: -5.0086
Max Act: 4.7274. Min Act: -0.1700
Data Index: 4716958 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19