Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1463 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0173. Min Range: -1.0173

Max Act: 1.0018. Min Act: -0.0001

Data Index: 638906 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 1.0173. Min Range: -1.0173

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1009064 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9276. Min Act: -0.0001

Data Index: 118633 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1044186 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8720. Min Act: -0.0001

Data Index: 689978 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8289. Min Act: -0.0001

Data Index: 209753 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8595. Min Act: -0.0001

Data Index: 248620 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1185565 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7239. Min Act: -0.0001

Data Index: 1045698 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1269207 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7607. Min Act: -0.0001

Data Index: 544678 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6823. Min Act: -0.0001

Data Index: 545752 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6878. Min Act: -0.0001

Data Index: 670429 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7116. Min Act: -0.0001

Data Index: 1174658 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7184. Min Act: -0.0001

Data Index: 1099249 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6762. Min Act: -0.0001

Data Index: 851191 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7092. Min Act: -0.0001

Data Index: 736245 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6918. Min Act: -0.0001

Data Index: 1398339 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6678. Min Act: -0.0001

Data Index: 1451573 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1242158 (C4 (Web Text))

Max Activating Token Index: 922