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

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

Neuron 5413 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: 1.2218. Min Range: -1.2218

Max Act: 1.2218. Min Act: -0.0000

Data Index: 365912 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.1599. Min Act: -0.0000

Data Index: 598721 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.2218. Min Range: -1.2218

Max Act: 1.0047. Min Act: -0.0000

Data Index: 727474 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1310173 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8451. Min Act: -0.0000

Data Index: 78954 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1249539 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1256095 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8744. Min Act: -0.0000

Data Index: 252014 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8190. Min Act: -0.0000

Data Index: 277303 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8311. Min Act: -0.0000

Data Index: 50388 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.8019. Min Act: -0.0000

Data Index: 255028 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7707. Min Act: -0.0000

Data Index: 851835 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1040207 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1114122 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1267262 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7271. Min Act: -0.0000

Data Index: 919476 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1013322 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1337957 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1145630 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 1.2218. Min Range: -1.2218

Max Act: 0.7744. Min Act: -0.0000

Data Index: 232525 (C4 (Web Text))

Max Activating Token Index: 380