Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.7368. Min Act: -0.1700
Data Index: 5544278 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.6118. Min Act: -0.1700
Data Index: 243144 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.3930. Min Act: -0.1700
Data Index: 2156893 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.3618. Min Act: -0.1700
Data Index: 4296778 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.3305. Min Act: -0.1700
Data Index: 1322343 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.3305. Min Act: -0.1700
Data Index: 7364000 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.2993. Min Act: -0.1700
Data Index: 1018424 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.2055. Min Act: -0.1700
Data Index: 4846028 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1743. Min Act: -0.1700
Data Index: 5907562 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1743. Min Act: -0.1700
Data Index: 2036694 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1430. Min Act: -0.1700
Data Index: 8697844 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1430. Min Act: -0.1700
Data Index: 2710086 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1743. Min Act: -0.1700
Data Index: 4309631 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1430. Min Act: -0.1700
Data Index: 3830639 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1118. Min Act: -0.1700
Data Index: 2633113 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.0805. Min Act: -0.1700
Data Index: 7208771 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.1118. Min Act: -0.1700
Data Index: 3784457 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.0805. Min Act: -0.1700
Data Index: 8038040 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.0805. Min Act: -0.1700
Data Index: 673815 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7368. Min Range: -7.7368
Max Act: 7.0493. Min Act: -0.1700
Data Index: 43100 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19