Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3849. Min Range: -4.3849
Max Act: 4.3849. Min Act: -0.1700
Data Index: 745140 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3849. Min Range: -4.3849
Max Act: 4.2599. Min Act: -0.1700
Data Index: 8326978 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3849. Min Range: -4.3849
Max Act: 4.2911. Min Act: -0.1700
Data Index: 8299187 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3849. Min Range: -4.3849
Max Act: 4.2599. Min Act: -0.1700
Data Index: 2733867 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3849. Min Range: -4.3849
Max Act: 4.1348. Min Act: -0.1700
Data Index: 5868886 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9785. Min Act: -0.1700
Data Index: 1559195 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9785. Min Act: -0.1700
Data Index: 3255889 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9473. Min Act: -0.1700
Data Index: 4556338 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9317. Min Act: -0.1700
Data Index: 3681887 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9317. Min Act: -0.1700
Data Index: 4731513 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9004. Min Act: -0.1700
Data Index: 5130381 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.9004. Min Act: -0.1700
Data Index: 5833019 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8535. Min Act: -0.1700
Data Index: 1143192 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8691. Min Act: -0.1700
Data Index: 7550623 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8378. Min Act: -0.1700
Data Index: 7349878 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8222. Min Act: -0.1700
Data Index: 4817424 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8066. Min Act: -0.1700
Data Index: 5880825 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8222. Min Act: -0.1700
Data Index: 3744513 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8066. Min Act: -0.1700
Data Index: 3878138 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3849. Min Range: -4.3849
Max Act: 3.8378. Min Act: -0.1700
Data Index: 2924308 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19