Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.1265. Min Act: -0.1700
Data Index: 7371619 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0952. Min Act: -0.1700
Data Index: 6553667 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0952. Min Act: -0.1700
Data Index: 7993044 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0640. Min Act: -0.1700
Data Index: 6516659 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0327. Min Act: -0.1700
Data Index: 1653309 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0640. Min Act: -0.1700
Data Index: 2107486 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0327. Min Act: -0.1700
Data Index: 1856510 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0015. Min Act: -0.1700
Data Index: 5411952 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1265. Min Range: -6.1265
Max Act: 6.0015. Min Act: -0.1700
Data Index: 2150265 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.9077. Min Act: -0.1700
Data Index: 3183134 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.9077. Min Act: -0.1700
Data Index: 3081102 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8765. Min Act: -0.1700
Data Index: 7317945 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8452. Min Act: -0.1700
Data Index: 8309348 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8765. Min Act: -0.1700
Data Index: 1530364 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8452. Min Act: -0.1700
Data Index: 4276479 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8140. Min Act: -0.1700
Data Index: 1530368 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8140. Min Act: -0.1700
Data Index: 2690033 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.8140. Min Act: -0.1700
Data Index: 3795671 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.7827. Min Act: -0.1700
Data Index: 3083595 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1265. Min Range: -6.1265
Max Act: 5.7202. Min Act: -0.1700
Data Index: 515670 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19