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

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

Neuron 2435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.3112. Min Act: -0.0000

Data Index: 1035810 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.2229. Min Act: -0.0000

Data Index: 949555 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.1653. Min Act: -0.0000

Data Index: 794814 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.0833. Min Act: -0.0000

Data Index: 463632 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.8439. Min Act: -0.0000

Data Index: 426157 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.7590. Min Act: -0.0000

Data Index: 1045746 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.7433. Min Act: -0.0000

Data Index: 90208 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.5583. Min Act: -0.0000

Data Index: 1044589 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 4.3112. Min Range: -4.3112

Max Act: 4.0674. Min Act: -0.0000

Data Index: 786448 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.6206. Min Act: -0.0000

Data Index: 1192636 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.2364. Min Act: -0.0000

Data Index: 655741 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.5296. Min Act: -0.0000

Data Index: 1282411 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.4492. Min Act: -0.0000

Data Index: 1312918 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 4.3112. Min Range: -4.3112

Max Act: 2.9967. Min Act: -0.0000

Data Index: 994260 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.4085. Min Act: -0.0000

Data Index: 615706 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.3381. Min Act: -0.0000

Data Index: 428547 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.3216. Min Act: -0.0000

Data Index: 1115687 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.0195. Min Act: -0.0000

Data Index: 1181380 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.1173. Min Act: -0.0000

Data Index: 1222332 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 4.3112. Min Range: -4.3112

Max Act: 3.1254. Min Act: -0.0000

Data Index: 295626 (C4 (Web Text))

Max Activating Token Index: 644