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

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

Neuron 4122 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: 3.0445. Min Range: -3.0445

Max Act: 2.5041. Min Act: -0.0000

Data Index: 1160318 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.0445. Min Range: -3.0445

Max Act: 3.0445. Min Act: -0.0001

Data Index: 286092 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1166066 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.4275. Min Act: -0.0000

Data Index: 1326444 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0754. Min Act: -0.0000

Data Index: 666313 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.3054. Min Act: -0.0000

Data Index: 589527 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.1846. Min Act: -0.0000

Data Index: 376596 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0787. Min Act: -0.0001

Data Index: 730241 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0174. Min Act: -0.0000

Data Index: 138573 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.1011. Min Act: -0.0000

Data Index: 130477 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0658. Min Act: -0.0000

Data Index: 345304 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0162. Min Act: -0.0000

Data Index: 315848 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0441. Min Act: -0.0001

Data Index: 1159177 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.1182. Min Act: -0.0001

Data Index: 1122608 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.1133. Min Act: -0.0000

Data Index: 254830 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.1714. Min Act: -0.0001

Data Index: 615814 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 3.0445. Min Range: -3.0445

Max Act: 2.0402. Min Act: -0.0001

Data Index: 536854 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 3.0445. Min Range: -3.0445

Max Act: 1.9294. Min Act: -0.0000

Data Index: 543034 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.0445. Min Range: -3.0445

Max Act: 1.9222. Min Act: -0.0000

Data Index: 1035900 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 3.0445. Min Range: -3.0445

Max Act: 1.9160. Min Act: -0.0000

Data Index: 790681 (C4 (Web Text))

Max Activating Token Index: 438