Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 422 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1738. Min Range: -5.1738
Max Act: 5.1738. Min Act: -0.1700
Data Index: 5724733 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1738. Min Range: -5.1738
Max Act: 5.0175. Min Act: -0.1700
Data Index: 2262354 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.9863. Min Act: -0.1700
Data Index: 8699005 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.9238. Min Act: -0.1700
Data Index: 5456221 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4544523 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.9238. Min Act: -0.1700
Data Index: 5243674 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4123541 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.8925. Min Act: -0.1700
Data Index: 4428931 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.8613. Min Act: -0.1700
Data Index: 5444784 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.8613. Min Act: -0.1700
Data Index: 2310734 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.8300. Min Act: -0.1700
Data Index: 224695 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.8300. Min Act: -0.1700
Data Index: 5602922 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7675. Min Act: -0.1700
Data Index: 1558247 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7988. Min Act: -0.1700
Data Index: 8199198 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7363. Min Act: -0.1700
Data Index: 72823 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7675. Min Act: -0.1700
Data Index: 6154615 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7050. Min Act: -0.1700
Data Index: 6526150 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5236462 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7363. Min Act: -0.1700
Data Index: 6999463 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1738. Min Range: -5.1738
Max Act: 4.7363. Min Act: -0.1700
Data Index: 8199190 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19