Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.7878. Min Act: -0.1700
Data Index: 137667 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.7878. Min Act: -0.1700
Data Index: 4414231 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.6940. Min Act: -0.1700
Data Index: 1698739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.5690. Min Act: -0.1700
Data Index: 1275666 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.5065. Min Act: -0.1700
Data Index: 6127656 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.5065. Min Act: -0.1700
Data Index: 6632496 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.5065. Min Act: -0.1700
Data Index: 2825666 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.4753. Min Act: -0.1700
Data Index: 144469 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.4753. Min Act: -0.1700
Data Index: 2835589 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.4440. Min Act: -0.1700
Data Index: 2013049 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6076655 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.4128. Min Act: -0.1700
Data Index: 697484 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3815. Min Act: -0.1700
Data Index: 5203398 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3815. Min Act: -0.1700
Data Index: 4690819 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3815. Min Act: -0.1700
Data Index: 8673628 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3815. Min Act: -0.1700
Data Index: 8261268 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3190. Min Act: -0.1700
Data Index: 2462099 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3503. Min Act: -0.1700
Data Index: 5167933 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6468679 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7878. Min Range: -6.7878
Max Act: 6.2878. Min Act: -0.1700
Data Index: 1271902 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19