Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.3585. Min Act: -0.1700
Data Index: 3850159 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.3273. Min Act: -0.1700
Data Index: 1295312 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.2648. Min Act: -0.1700
Data Index: 5557559 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.1710. Min Act: -0.1700
Data Index: 2037853 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.1710. Min Act: -0.1700
Data Index: 3052845 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.1085. Min Act: -0.1700
Data Index: 3465018 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6096758 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.0147. Min Act: -0.1700
Data Index: 2005241 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.0147. Min Act: -0.1700
Data Index: 6592554 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.0147. Min Act: -0.1700
Data Index: 2345425 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3585. Min Range: -4.3585
Max Act: 4.0147. Min Act: -0.1700
Data Index: 1839307 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.9522. Min Act: -0.1700
Data Index: 7093237 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.9209. Min Act: -0.1700
Data Index: 7701576 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.9522. Min Act: -0.1700
Data Index: 5068087 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.8271. Min Act: -0.1700
Data Index: 8729072 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.8584. Min Act: -0.1700
Data Index: 699970 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.8584. Min Act: -0.1700
Data Index: 5272516 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.8271. Min Act: -0.1700
Data Index: 1384509 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.7958. Min Act: -0.1700
Data Index: 8706079 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3585. Min Range: -4.3585
Max Act: 3.8271. Min Act: -0.1700
Data Index: 6693883 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19