Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4031 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4275. Min Act: -0.0000

Data Index: 580922 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4208. Min Act: -0.0000

Data Index: 319095 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3969. Min Act: -0.0000

Data Index: 216127 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3508. Min Act: -0.0000

Data Index: 646713 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1321392 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3255. Min Act: -0.0000

Data Index: 438907 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3293. Min Act: -0.0000

Data Index: 866814 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3125. Min Act: -0.0000

Data Index: 680917 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2940. Min Act: -0.0000

Data Index: 103004 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3065. Min Act: -0.0000

Data Index: 217803 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2622. Min Act: -0.0000

Data Index: 845613 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1253958 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2533. Min Act: -0.0000

Data Index: 979221 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2785. Min Act: -0.0000

Data Index: 891987 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2665. Min Act: -0.0000

Data Index: 423622 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2656. Min Act: -0.0000

Data Index: 550257 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1066168 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2700. Min Act: -0.0000

Data Index: 103128 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1208968 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2576. Min Act: -0.0000

Data Index: 678302 (C4 (Web Text))

Max Activating Token Index: 934