Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.6976. Min Act: -0.1700
Data Index: 3527565 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.6976. Min Act: -0.1700
Data Index: 6330246 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.6013. Min Act: -0.1700
Data Index: 3034674 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5852. Min Act: -0.1700
Data Index: 7824136 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5368. Min Act: -0.1700
Data Index: 6158249 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5368. Min Act: -0.1700
Data Index: 2493414 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 4139193 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 954599 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 4964325 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 6554388 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 1839062 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4883. Min Act: -0.1700
Data Index: 306964 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5045. Min Act: -0.1700
Data Index: 8766734 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.5207. Min Act: -0.1700
Data Index: 2914660 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4883. Min Act: -0.1700
Data Index: 7655287 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4395. Min Act: -0.1700
Data Index: 2858929 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4558. Min Act: -0.1700
Data Index: 6793900 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4883. Min Act: -0.1700
Data Index: 698876 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4720. Min Act: -0.1700
Data Index: 6749305 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6976. Min Range: -2.6976
Max Act: 2.4395. Min Act: -0.1700
Data Index: 5621553 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19