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

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

Neuron 5633 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: 2.3701. Min Range: -2.3701

Max Act: 2.3701. Min Act: -0.0000

Data Index: 929728 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.3701. Min Range: -2.3701

Max Act: 2.2225. Min Act: -0.0000

Data Index: 1209738 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 2.3701. Min Range: -2.3701

Max Act: 2.0141. Min Act: -0.0000

Data Index: 340963 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.9531. Min Act: -0.0000

Data Index: 367661 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.9906. Min Act: -0.0000

Data Index: 103195 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1347062 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1270036 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1020677 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1227917 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5744. Min Act: -0.0000

Data Index: 53116 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5848. Min Act: -0.0000

Data Index: 321446 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5326. Min Act: -0.0000

Data Index: 204660 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5289. Min Act: -0.0000

Data Index: 607004 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5346. Min Act: -0.0000

Data Index: 1201404 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.4962. Min Act: -0.0000

Data Index: 380507 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1015410 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.5478. Min Act: -0.0000

Data Index: 478370 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.4502. Min Act: -0.0000

Data Index: 919440 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.3730. Min Act: -0.0000

Data Index: 286186 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.3701. Min Range: -2.3701

Max Act: 1.4454. Min Act: -0.0000

Data Index: 547675 (C4 (Web Text))

Max Activating Token Index: 21