Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.4442. Min Act: -0.1700
Data Index: 3534655 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.2567. Min Act: -0.1700
Data Index: 3344254 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.3192. Min Act: -0.1700
Data Index: 3412932 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.2567. Min Act: -0.1700
Data Index: 5691257 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.1942. Min Act: -0.1700
Data Index: 4305755 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.1942. Min Act: -0.1700
Data Index: 4177290 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.1942. Min Act: -0.1700
Data Index: 211891 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4442. Min Range: -8.4442
Max Act: 8.0067. Min Act: -0.1700
Data Index: 7884705 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.9442. Min Act: -0.1700
Data Index: 789614 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.9442. Min Act: -0.1700
Data Index: 5925237 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.9442. Min Act: -0.1700
Data Index: 1204040 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.9130. Min Act: -0.1700
Data Index: 3830099 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.9442. Min Act: -0.1700
Data Index: 500592 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8817. Min Act: -0.1700
Data Index: 6905910 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8817. Min Act: -0.1700
Data Index: 5883264 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8817. Min Act: -0.1700
Data Index: 7488176 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8505. Min Act: -0.1700
Data Index: 5512361 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8505. Min Act: -0.1700
Data Index: 351297 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.8505. Min Act: -0.1700
Data Index: 6689500 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4442. Min Range: -8.4442
Max Act: 7.7880. Min Act: -0.1700
Data Index: 5207842 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19