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

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

Neuron 3415 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.0797. Min Act: -0.0000

Data Index: 492559 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.1324. Min Act: -0.0000

Data Index: 1097068 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.1342. Min Act: -0.0000

Data Index: 813180 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.1036. Min Act: -0.0000

Data Index: 570478 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.0975. Min Act: -0.0000

Data Index: 952035 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.0733. Min Act: -0.0000

Data Index: 797240 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.0583. Min Act: -0.0000

Data Index: 60669 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.9920. Min Act: -0.0000

Data Index: 134089 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.9961. Min Act: -0.0000

Data Index: 1097708 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.1355. Min Act: -0.0000

Data Index: 841899 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.9297. Min Act: -0.0000

Data Index: 51822 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.7728. Min Act: -0.0000

Data Index: 1242080 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.0920. Min Act: -0.0000

Data Index: 288895 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.2384. Min Act: -0.0000

Data Index: 1090708 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.7316. Min Act: -0.0000

Data Index: 297413 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 4.2384. Min Range: -4.2384

Max Act: 4.1838. Min Act: -0.0000

Data Index: 754415 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.7115. Min Act: -0.0000

Data Index: 726394 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.8495. Min Act: -0.0000

Data Index: 1020609 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.8444. Min Act: -0.0000

Data Index: 158264 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 4.2384. Min Range: -4.2384

Max Act: 3.7950. Min Act: -0.0000

Data Index: 278457 (C4 (Web Text))

Max Activating Token Index: 173