Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1676. Min Range: -6.1676
Max Act: 6.1676. Min Act: -0.1700
Data Index: 7370398 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1676. Min Range: -6.1676
Max Act: 6.0738. Min Act: -0.1700
Data Index: 2107507 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1676. Min Range: -6.1676
Max Act: 6.0738. Min Act: -0.1700
Data Index: 6013429 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1676. Min Range: -6.1676
Max Act: 6.0113. Min Act: -0.1700
Data Index: 4386408 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.9801. Min Act: -0.1700
Data Index: 1525342 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.9488. Min Act: -0.1700
Data Index: 4231858 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.9176. Min Act: -0.1700
Data Index: 2764939 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.9176. Min Act: -0.1700
Data Index: 1067896 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4350797 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8863. Min Act: -0.1700
Data Index: 3480098 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8863. Min Act: -0.1700
Data Index: 8412098 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8551. Min Act: -0.1700
Data Index: 2473988 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8551. Min Act: -0.1700
Data Index: 5084882 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8551. Min Act: -0.1700
Data Index: 8375911 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8238. Min Act: -0.1700
Data Index: 7051671 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8551. Min Act: -0.1700
Data Index: 6115834 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.8551. Min Act: -0.1700
Data Index: 6612494 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.7613. Min Act: -0.1700
Data Index: 5859131 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.7926. Min Act: -0.1700
Data Index: 7243830 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1676. Min Range: -6.1676
Max Act: 5.7926. Min Act: -0.1700
Data Index: 6632042 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19