Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5269. Min Act: -0.0000

Data Index: 618809 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4363. Min Act: -0.0000

Data Index: 821270 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4506. Min Act: -0.0000

Data Index: 844044 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1026535 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1183217 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3372. Min Act: -0.0001

Data Index: 411026 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2987. Min Act: -0.0001

Data Index: 568083 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3242. Min Act: -0.0001

Data Index: 1493948 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2902. Min Act: -0.0001

Data Index: 88868 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2635. Min Act: -0.0001

Data Index: 28604 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1190475 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2885. Min Act: -0.0001

Data Index: 600581 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2550. Min Act: -0.0001

Data Index: 608835 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2550. Min Act: -0.0001

Data Index: 108287 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2527. Min Act: -0.0001

Data Index: 954697 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2182. Min Act: -0.0001

Data Index: 216158 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2284. Min Act: -0.0001

Data Index: 719037 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2491. Min Act: -0.0000

Data Index: 366535 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2325. Min Act: -0.0001

Data Index: 354103 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1577349 (Python Code)

Max Activating Token Index: 113