Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1129. Min Range: -6.1129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 5096753 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1129. Min Range: -6.1129
Max Act: 6.1129. Min Act: -0.1700
Data Index: 2204000 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.9879. Min Act: -0.1700
Data Index: 3698501 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.9254. Min Act: -0.1700
Data Index: 8351530 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.8629. Min Act: -0.1700
Data Index: 4113857 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.7379. Min Act: -0.1700
Data Index: 1162952 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.7067. Min Act: -0.1700
Data Index: 7789876 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6754. Min Act: -0.1700
Data Index: 2781802 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6442. Min Act: -0.1700
Data Index: 727239 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6442. Min Act: -0.1700
Data Index: 1816966 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6757971 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6442. Min Act: -0.1700
Data Index: 1367687 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6129. Min Act: -0.1700
Data Index: 6550136 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5817. Min Act: -0.1700
Data Index: 6498452 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.6129. Min Act: -0.1700
Data Index: 7508333 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5906066 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5817. Min Act: -0.1700
Data Index: 3697174 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8717083 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1897541 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1129. Min Range: -6.1129
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1847223 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19