Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1758 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2814. Min Act: -0.1700
Data Index: 7984600 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2814. Min Act: -0.1700
Data Index: 5883333 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2501. Min Act: -0.1700
Data Index: 4662811 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2189. Min Act: -0.1700
Data Index: 4489861 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2189. Min Act: -0.1700
Data Index: 3031596 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.2189. Min Act: -0.1700
Data Index: 504906 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1876. Min Act: -0.1700
Data Index: 7515191 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1876. Min Act: -0.1700
Data Index: 1093278 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1876. Min Act: -0.1700
Data Index: 5553982 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 2179710 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 1686717 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 5587493 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 2210483 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 8058512 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.0939. Min Act: -0.1700
Data Index: 5302020 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1564. Min Act: -0.1700
Data Index: 7729669 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1251. Min Act: -0.1700
Data Index: 7624100 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1251. Min Act: -0.1700
Data Index: 6753317 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1251. Min Act: -0.1700
Data Index: 1590630 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2814. Min Range: -6.2814
Max Act: 6.1251. Min Act: -0.1700
Data Index: 4090374 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19