Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0369. Min Range: -8.0369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 500505 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.7244. Min Act: -0.1700
Data Index: 367180 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.7244. Min Act: -0.1700
Data Index: 4417584 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.6931. Min Act: -0.1700
Data Index: 2839775 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.6306. Min Act: -0.1700
Data Index: 4950024 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.5056. Min Act: -0.1700
Data Index: 408098 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4744. Min Act: -0.1700
Data Index: 6140859 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4744. Min Act: -0.1700
Data Index: 5401633 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4744. Min Act: -0.1700
Data Index: 2839773 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4431. Min Act: -0.1700
Data Index: 6506906 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4431. Min Act: -0.1700
Data Index: 5778150 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4119. Min Act: -0.1700
Data Index: 7793959 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3806. Min Act: -0.1700
Data Index: 8456084 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3494. Min Act: -0.1700
Data Index: 5379112 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3181. Min Act: -0.1700
Data Index: 400697 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2869. Min Act: -0.1700
Data Index: 5864910 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2869. Min Act: -0.1700
Data Index: 3633980 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2556. Min Act: -0.1700
Data Index: 1728238 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2556. Min Act: -0.1700
Data Index: 4836842 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2556. Min Act: -0.1700
Data Index: 3516047 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19