Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.7694. Min Range: -16.7694
Max Act: 16.7694. Min Act: -0.1700
Data Index: 7833561 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.7694. Min Range: -16.7694
Max Act: 16.3944. Min Act: -0.1700
Data Index: 7833557 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.7694. Min Range: -16.7694
Max Act: 16.2694. Min Act: -0.1700
Data Index: 7833559 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.7694. Min Range: -16.7694
Max Act: 16.1444. Min Act: -0.1700
Data Index: 3454808 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.7694. Min Range: -16.7694
Max Act: 16.1444. Min Act: -0.1700
Data Index: 7833551 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.7694. Min Act: -0.1700
Data Index: 1108570 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.7694. Min Act: -0.1700
Data Index: 47227 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.6444. Min Act: -0.1700
Data Index: 3454809 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.6444. Min Act: -0.1700
Data Index: 4040082 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.5819. Min Act: -0.1700
Data Index: 1044850 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.5819. Min Act: -0.1700
Data Index: 7818239 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.3319. Min Act: -0.1700
Data Index: 47226 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.2069. Min Act: -0.1700
Data Index: 459242 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.2069. Min Act: -0.1700
Data Index: 5194022 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0819. Min Act: -0.1700
Data Index: 7818224 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0819. Min Act: -0.1700
Data Index: 7872990 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0819. Min Act: -0.1700
Data Index: 7160958 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0194. Min Act: -0.1700
Data Index: 6153055 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0194. Min Act: -0.1700
Data Index: 2721784 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.7694. Min Range: -16.7694
Max Act: 15.0194. Min Act: -0.1700
Data Index: 2838012 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19