Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.4373. Min Act: -0.1700
Data Index: 7977142 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.2186. Min Act: -0.1700
Data Index: 4776613 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.2186. Min Act: -0.1700
Data Index: 4776611 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.1561. Min Act: -0.1700
Data Index: 4805256 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.1561. Min Act: -0.1700
Data Index: 4776610 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 5567271 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 2262358 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 3758351 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 6450308 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 269325 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 906867 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0311. Min Act: -0.1700
Data Index: 2806499 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1700
Data Index: 7023724 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1700
Data Index: 1328607 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1700
Data Index: 8107565 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1698
Data Index: 6402969 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1700
Data Index: 1129474 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9998. Min Act: -0.1700
Data Index: 5184430 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9686. Min Act: -0.1700
Data Index: 7835558 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.9061. Min Act: -0.1700
Data Index: 3258241 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19