Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.9738. Min Act: -0.1700
Data Index: 1149401 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.9113. Min Act: -0.1700
Data Index: 413570 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.8800. Min Act: -0.1700
Data Index: 7085712 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.8175. Min Act: -0.1700
Data Index: 1821748 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.8488. Min Act: -0.1700
Data Index: 270707 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.8175. Min Act: -0.1700
Data Index: 8649297 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7863. Min Act: -0.1700
Data Index: 3605184 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6101989 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7863. Min Act: -0.1700
Data Index: 4450459 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7550. Min Act: -0.1700
Data Index: 1365280 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7238. Min Act: -0.1700
Data Index: 5985409 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.6925. Min Act: -0.1700
Data Index: 2684758 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7550. Min Act: -0.1700
Data Index: 643280 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7238. Min Act: -0.1700
Data Index: 8832733 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7238. Min Act: -0.1700
Data Index: 1258879 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7238. Min Act: -0.1700
Data Index: 1052891 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.7238. Min Act: -0.1700
Data Index: 1240013 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.6925. Min Act: -0.1700
Data Index: 3130682 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.6613. Min Act: -0.1700
Data Index: 2218112 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9738. Min Range: -6.9738
Max Act: 6.6613. Min Act: -0.1700
Data Index: 34209 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19