Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8938. Min Act: -0.1700
Data Index: 636704 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8625. Min Act: -0.1700
Data Index: 355054 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8625. Min Act: -0.1700
Data Index: 3409553 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8625. Min Act: -0.1700
Data Index: 3278776 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7055759 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8313. Min Act: -0.1700
Data Index: 4065672 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8000. Min Act: -0.1700
Data Index: 5085310 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4360375 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 7347488 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5366759 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 908404 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 7901922 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 1672887 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.6750. Min Act: -0.1700
Data Index: 1588741 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 167458 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.6750. Min Act: -0.1700
Data Index: 8631830 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 1037595 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.6438. Min Act: -0.1700
Data Index: 6387533 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.6438. Min Act: -0.1700
Data Index: 279789 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8938. Min Range: -5.8938
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2425540 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19