Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.2342. Min Act: -0.1700
Data Index: 551007 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.2342. Min Act: -0.1700
Data Index: 8814851 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.2029. Min Act: -0.1700
Data Index: 3806424 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.2029. Min Act: -0.1700
Data Index: 8217619 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.2029. Min Act: -0.1700
Data Index: 4070975 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1584860 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.1404. Min Act: -0.1700
Data Index: 5114290 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.1404. Min Act: -0.1700
Data Index: 2325755 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.1404. Min Act: -0.1700
Data Index: 2418999 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.1404. Min Act: -0.1700
Data Index: 6418891 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0779. Min Act: -0.1700
Data Index: 2369565 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0467. Min Act: -0.1700
Data Index: 2369564 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0467. Min Act: -0.1700
Data Index: 972619 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0154. Min Act: -0.1700
Data Index: 1584866 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0467. Min Act: -0.1700
Data Index: 968749 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0467. Min Act: -0.1700
Data Index: 2506004 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1584865 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0154. Min Act: -0.1700
Data Index: 5900473 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0154. Min Act: -0.1700
Data Index: 1448621 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2342. Min Range: -5.2342
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6466016 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19