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

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

Neuron 5106 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3228. Min Act: -0.0002

Data Index: 204322 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3397. Min Act: -0.0003

Data Index: 300325 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3318. Min Act: -0.0003

Data Index: 856993 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3025. Min Act: -0.0003

Data Index: 770664 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2921. Min Act: -0.0002

Data Index: 1332453 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3038. Min Act: -0.0003

Data Index: 121843 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2780. Min Act: -0.0003

Data Index: 795595 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2731. Min Act: -0.0003

Data Index: 584709 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2819. Min Act: -0.0003

Data Index: 835424 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2619. Min Act: -0.0003

Data Index: 333198 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2529. Min Act: -0.0003

Data Index: 937107 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2520. Min Act: -0.0003

Data Index: 260611 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2420. Min Act: -0.0003

Data Index: 734074 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2572. Min Act: -0.0003

Data Index: 989294 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2477. Min Act: -0.0003

Data Index: 1188088 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2567. Min Act: -0.0003

Data Index: 715341 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2481. Min Act: -0.0003

Data Index: 431693 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2358. Min Act: -0.0002

Data Index: 1354681 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2530. Min Act: -0.0003

Data Index: 642973 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2389. Min Act: -0.0003

Data Index: 612677 (C4 (Web Text))

Max Activating Token Index: 459