Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3060 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1757. Min Act: -0.1700
Data Index: 4279649 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1444. Min Act: -0.1700
Data Index: 1229690 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 3272240 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 5963222 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0194. Min Act: -0.1700
Data Index: 3953915 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8787. Min Act: -0.1700
Data Index: 5220378 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8474. Min Act: -0.1700
Data Index: 2499473 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8474. Min Act: -0.1700
Data Index: 6327521 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8474. Min Act: -0.1700
Data Index: 5409725 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8474. Min Act: -0.1700
Data Index: 6639346 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.8162. Min Act: -0.1700
Data Index: 8654258 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7849. Min Act: -0.1700
Data Index: 3953918 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7536. Min Act: -0.1700
Data Index: 7254136 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7536. Min Act: -0.1700
Data Index: 3629914 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7380. Min Act: -0.1700
Data Index: 5566423 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7223. Min Act: -0.1700
Data Index: 8782370 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7223. Min Act: -0.1700
Data Index: 6327518 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7067. Min Act: -0.1700
Data Index: 4915103 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7067. Min Act: -0.1700
Data Index: 6213308 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1757. Min Range: -4.1757
Max Act: 3.7067. Min Act: -0.1700
Data Index: 6083080 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19