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

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

Neuron 4154 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5134. Min Range: -4.5134

Max Act: 4.5134. Min Act: -0.0000

Data Index: 386915 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.7078. Min Act: -0.0000

Data Index: 375161 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.4326. Min Act: -0.0000

Data Index: 773713 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1238460 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.1489. Min Act: -0.0000

Data Index: 401126 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.2833. Min Act: -0.0000

Data Index: 350597 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.2569. Min Act: -0.0000

Data Index: 601076 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.2164. Min Act: -0.0000

Data Index: 694327 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.1711. Min Act: -0.0000

Data Index: 813586 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.9210. Min Act: -0.0000

Data Index: 245098 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.1452. Min Act: -0.0000

Data Index: 817103 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.1077. Min Act: -0.0000

Data Index: 1116285 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.2285. Min Act: -0.0000

Data Index: 1120469 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.7211. Min Act: -0.0000

Data Index: 590201 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.0242. Min Act: -0.0000

Data Index: 1058192 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.9180. Min Act: -0.0000

Data Index: 111602 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.8807. Min Act: -0.0000

Data Index: 424126 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 4.5134. Min Range: -4.5134

Max Act: 3.0441. Min Act: -0.0000

Data Index: 1277896 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.8289. Min Act: -0.0000

Data Index: 337703 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 4.5134. Min Range: -4.5134

Max Act: 2.8564. Min Act: -0.0000

Data Index: 802542 (C4 (Web Text))

Max Activating Token Index: 760