Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.7910. Min Act: -0.1700
Data Index: 3903323 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.5563. Min Act: -0.1700
Data Index: 1507578 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.5250. Min Act: -0.1700
Data Index: 2984974 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.5250. Min Act: -0.1700
Data Index: 488986 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.4937. Min Act: -0.1700
Data Index: 959427 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.4467. Min Act: -0.1700
Data Index: 2103617 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.4780. Min Act: -0.1700
Data Index: 1162936 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.4467. Min Act: -0.1700
Data Index: 2872775 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.4154. Min Act: -0.1700
Data Index: 2630113 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3997. Min Act: -0.1700
Data Index: 6794295 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3997. Min Act: -0.1700
Data Index: 5969422 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3840. Min Act: -0.1700
Data Index: 1499664 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3369. Min Act: -0.1700
Data Index: 2005474 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3369. Min Act: -0.1700
Data Index: 603837 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.3056. Min Act: -0.1700
Data Index: 4230537 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.2899. Min Act: -0.1700
Data Index: 6370344 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.2899. Min Act: -0.1700
Data Index: 3765572 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.2742. Min Act: -0.1700
Data Index: 34391 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.2584. Min Act: -0.1700
Data Index: 8140380 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7910. Min Range: -3.7910
Max Act: 3.2584. Min Act: -0.1700
Data Index: 7001898 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19