Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.4757. Min Act: -0.1700
Data Index: 4012730 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.3194. Min Act: -0.1700
Data Index: 7427611 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.2257. Min Act: -0.1700
Data Index: 7700892 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.1319. Min Act: -0.1700
Data Index: 3068492 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.1631. Min Act: -0.1700
Data Index: 349964 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.1319. Min Act: -0.1700
Data Index: 8132795 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.1006. Min Act: -0.1700
Data Index: 5175095 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.1006. Min Act: -0.1700
Data Index: 5650678 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0694. Min Act: -0.1700
Data Index: 2210511 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0381. Min Act: -0.1700
Data Index: 1724607 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0381. Min Act: -0.1700
Data Index: 6122795 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0381. Min Act: -0.1700
Data Index: 7066162 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0381. Min Act: -0.1700
Data Index: 3508854 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0069. Min Act: -0.1700
Data Index: 4308087 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4757. Min Range: -4.4757
Max Act: 4.0069. Min Act: -0.1700
Data Index: 2301780 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4757. Min Range: -4.4757
Max Act: 3.9756. Min Act: -0.1700
Data Index: 38731 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4757. Min Range: -4.4757
Max Act: 3.9756. Min Act: -0.1700
Data Index: 5463471 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4757. Min Range: -4.4757
Max Act: 3.9756. Min Act: -0.1700
Data Index: 7445514 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4757. Min Range: -4.4757
Max Act: 3.9756. Min Act: -0.1700
Data Index: 3783033 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4757. Min Range: -4.4757
Max Act: 3.9443. Min Act: -0.1700
Data Index: 748488 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19