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

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

Neuron 3708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1357378 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7415. Min Act: -0.0001

Data Index: 95368 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7451. Min Act: -0.0001

Data Index: 207986 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7693. Min Act: -0.0001

Data Index: 66968 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7167. Min Act: -0.0001

Data Index: 643962 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1204152 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6713. Min Act: -0.0001

Data Index: 376274 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1284140 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6415. Min Act: -0.0001

Data Index: 1269850 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6243. Min Act: -0.0001

Data Index: 1207508 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6165. Min Act: -0.0000

Data Index: 404215 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5855. Min Act: -0.0001

Data Index: 297567 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1267575 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6149. Min Act: -0.0000

Data Index: 401838 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5757. Min Act: -0.0001

Data Index: 435370 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5444. Min Act: -0.0001

Data Index: 645717 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5952. Min Act: -0.0001

Data Index: 884203 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5736. Min Act: -0.0000

Data Index: 415507 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5394. Min Act: -0.0001

Data Index: 927501 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.5828. Min Act: -0.0001

Data Index: 272517 (C4 (Web Text))

Max Activating Token Index: 587