Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.7246. Min Act: -0.1700
Data Index: 1508930 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.5996. Min Act: -0.1700
Data Index: 762626 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.5371. Min Act: -0.1700
Data Index: 6568905 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.5371. Min Act: -0.1700
Data Index: 3230885 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.4434. Min Act: -0.1700
Data Index: 96705 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.4434. Min Act: -0.1700
Data Index: 1680615 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6963562 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.4121. Min Act: -0.1700
Data Index: 1212620 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3809. Min Act: -0.1700
Data Index: 3822613 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6441759 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3809. Min Act: -0.1700
Data Index: 956780 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3809. Min Act: -0.1700
Data Index: 2857747 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4853810 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2871. Min Act: -0.1700
Data Index: 613288 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3785077 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2871. Min Act: -0.1700
Data Index: 6788828 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2559. Min Act: -0.1700
Data Index: 661468 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2871. Min Act: -0.1700
Data Index: 2376618 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2871. Min Act: -0.1700
Data Index: 5714036 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7246. Min Range: -4.7246
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1798027 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19