Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.7351. Min Act: -0.1700
Data Index: 1220970 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.7038. Min Act: -0.1700
Data Index: 575865 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5943. Min Act: -0.1700
Data Index: 7512288 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5943. Min Act: -0.1700
Data Index: 2231321 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5943. Min Act: -0.1700
Data Index: 1469819 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5473. Min Act: -0.1700
Data Index: 5348781 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5160. Min Act: -0.1700
Data Index: 5077632 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5160. Min Act: -0.1700
Data Index: 2426550 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5316. Min Act: -0.1700
Data Index: 2434308 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5003. Min Act: -0.1700
Data Index: 4993695 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.5003. Min Act: -0.1700
Data Index: 3697848 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4847. Min Act: -0.1700
Data Index: 3019928 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4847. Min Act: -0.1700
Data Index: 8431057 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4847. Min Act: -0.1700
Data Index: 3941520 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4690. Min Act: -0.1700
Data Index: 166954 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4533. Min Act: -0.1700
Data Index: 3147961 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4533. Min Act: -0.1700
Data Index: 4445854 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4533. Min Act: -0.1700
Data Index: 4394962 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4690. Min Act: -0.1700
Data Index: 3660440 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7351. Min Range: -3.7351
Max Act: 3.4533. Min Act: -0.1700
Data Index: 5844341 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19