Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1076 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.7560. Min Act: -0.1700
Data Index: 6760321 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.7248. Min Act: -0.1700
Data Index: 5322690 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.6623. Min Act: -0.1700
Data Index: 3756322 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5998. Min Act: -0.1700
Data Index: 1394369 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.5373. Min Act: -0.1700
Data Index: 7732616 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4747. Min Act: -0.1700
Data Index: 7570499 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 7998284 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 540576 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4435. Min Act: -0.1700
Data Index: 3075519 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.4122. Min Act: -0.1700
Data Index: 7174472 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3810. Min Act: -0.1700
Data Index: 1962305 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3810. Min Act: -0.1700
Data Index: 4269174 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3497. Min Act: -0.1700
Data Index: 4937883 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3497. Min Act: -0.1700
Data Index: 2115922 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3185. Min Act: -0.1700
Data Index: 3647036 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3810. Min Act: -0.1700
Data Index: 5103865 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.2872. Min Act: -0.1700
Data Index: 7303714 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3185. Min Act: -0.1700
Data Index: 799032 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.3185. Min Act: -0.1700
Data Index: 3539008 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7560. Min Range: -4.7560
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2293258 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19