Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1954. Min Range: -8.1954
Max Act: 8.1954. Min Act: -0.1700
Data Index: 2467387 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1954. Min Range: -8.1954
Max Act: 8.0079. Min Act: -0.1700
Data Index: 7418659 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.9454. Min Act: -0.1700
Data Index: 5471167 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.8829. Min Act: -0.1700
Data Index: 5510669 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.8204. Min Act: -0.1700
Data Index: 2035219 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.8204. Min Act: -0.1700
Data Index: 2153903 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.8204. Min Act: -0.1700
Data Index: 2254471 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.8204. Min Act: -0.1700
Data Index: 8371018 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 4685328 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.7266. Min Act: -0.1700
Data Index: 91708 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.7266. Min Act: -0.1700
Data Index: 346228 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6954. Min Act: -0.1700
Data Index: 6600213 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 4777278 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 1515199 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 1726321 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 3131213 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6016. Min Act: -0.1700
Data Index: 3550407 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 3811173 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 7129682 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1954. Min Range: -8.1954
Max Act: 7.6016. Min Act: -0.1700
Data Index: 5095718 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19