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

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

Neuron 253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0000

Data Index: 865553 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0352. Min Act: -0.0000

Data Index: 498586 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0358. Min Act: -0.0000

Data Index: 90017 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0346. Min Act: -0.0000

Data Index: 294998 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0316. Min Act: -0.0000

Data Index: 232126 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0289. Min Act: -0.0000

Data Index: 609055 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0341. Min Act: -0.0000

Data Index: 124572 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0353. Min Act: -0.0000

Data Index: 150091 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0338. Min Act: -0.0000

Data Index: 493271 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0321. Min Act: -0.0001

Data Index: 98195 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0330. Min Act: -0.0001

Data Index: 117312 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0308. Min Act: -0.0001

Data Index: 186905 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1100065 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0295. Min Act: -0.0000

Data Index: 176970 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0325. Min Act: -0.0000

Data Index: 261341 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0001

Data Index: 330612 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0302. Min Act: -0.0000

Data Index: 502972 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0000

Data Index: 220400 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0000

Data Index: 665183 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0334. Min Act: -0.0000

Data Index: 666009 (C4 (Web Text))

Max Activating Token Index: 289