Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.8919. Min Act: -0.1700
Data Index: 2488483 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.4857. Min Act: -0.1700
Data Index: 8821969 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.2044. Min Act: -0.1700
Data Index: 3158315 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.1107. Min Act: -0.1700
Data Index: 3622109 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.0482. Min Act: -0.1700
Data Index: 1672962 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.0482. Min Act: -0.1700
Data Index: 4905589 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8919. Min Range: -7.8919
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7937173 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 3995795 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 2806380 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9857. Min Act: -0.1700
Data Index: 2971355 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9544. Min Act: -0.1700
Data Index: 864429 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9232. Min Act: -0.1700
Data Index: 4221163 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.8919. Min Act: -0.1700
Data Index: 3491319 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.9232. Min Act: -0.1700
Data Index: 8240682 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.8919. Min Act: -0.1700
Data Index: 7805905 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.8919. Min Act: -0.1700
Data Index: 3331216 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.7982. Min Act: -0.1700
Data Index: 6737909 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.7982. Min Act: -0.1700
Data Index: 8093519 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.7982. Min Act: -0.1700
Data Index: 4964745 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8919. Min Range: -7.8919
Max Act: 6.7669. Min Act: -0.1700
Data Index: 3652891 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19