Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.2299. Min Act: -0.1700
Data Index: 5743034 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0737. Min Act: -0.1700
Data Index: 1336840 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0737. Min Act: -0.1700
Data Index: 8719946 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0424. Min Act: -0.1700
Data Index: 575866 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2299. Min Range: -5.2299
Max Act: 5.0112. Min Act: -0.1700
Data Index: 461284 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9799. Min Act: -0.1700
Data Index: 4089761 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.9174. Min Act: -0.1700
Data Index: 6298086 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.8862. Min Act: -0.1700
Data Index: 477117 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.8862. Min Act: -0.1700
Data Index: 5441253 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.8237. Min Act: -0.1700
Data Index: 7037786 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.8237. Min Act: -0.1700
Data Index: 503951 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7924. Min Act: -0.1700
Data Index: 4865569 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7924. Min Act: -0.1700
Data Index: 7233301 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7924. Min Act: -0.1700
Data Index: 5955099 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7612. Min Act: -0.1700
Data Index: 5588656 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7924. Min Act: -0.1700
Data Index: 7713692 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7612. Min Act: -0.1700
Data Index: 461286 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7612. Min Act: -0.1700
Data Index: 5475785 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7299. Min Act: -0.1700
Data Index: 4076678 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2299. Min Range: -5.2299
Max Act: 4.7299. Min Act: -0.1700
Data Index: 3324344 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19