Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.8327. Min Act: -0.1700
Data Index: 4037037 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.8155. Min Act: -0.1700
Data Index: 4730407 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7811. Min Act: -0.1700
Data Index: 8600537 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7811. Min Act: -0.1700
Data Index: 3809012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7466. Min Act: -0.1700
Data Index: 8384712 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7466. Min Act: -0.1700
Data Index: 8600531 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7466. Min Act: -0.1699
Data Index: 6970418 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7466. Min Act: -0.1700
Data Index: 700756 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7466. Min Act: -0.1700
Data Index: 5792775 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.7293. Min Act: -0.1700
Data Index: 1822101 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6947. Min Act: -0.1700
Data Index: 6922017 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6947. Min Act: -0.1699
Data Index: 5163167 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 6321114 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 5862771 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 691418 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6599. Min Act: -0.1700
Data Index: 7307563 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 7940060 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 8340982 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 669967 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8327. Min Range: -1.8327
Max Act: 1.6773. Min Act: -0.1700
Data Index: 4189807 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19