Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1434 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6975. Min Act: -0.0002

Data Index: 1166985 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.7428. Min Act: -0.0001

Data Index: 81812 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6332. Min Act: -0.0001

Data Index: 1043197 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6824. Min Act: -0.0001

Data Index: 836951 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6488. Min Act: -0.0002

Data Index: 43210 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6442. Min Act: -0.0001

Data Index: 983018 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5951. Min Act: -0.0002

Data Index: 861453 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1112335 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6333. Min Act: -0.0002

Data Index: 326284 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.6343. Min Act: -0.0002

Data Index: 799208 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5567. Min Act: -0.0002

Data Index: 843880 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5685. Min Act: -0.0001

Data Index: 745814 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5343. Min Act: -0.0002

Data Index: 533581 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5172. Min Act: -0.0002

Data Index: 319955 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5654. Min Act: -0.0001

Data Index: 443686 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5506. Min Act: -0.0002

Data Index: 1231648 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5465. Min Act: -0.0001

Data Index: 501138 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5616. Min Act: -0.0001

Data Index: 452102 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5230. Min Act: -0.0002

Data Index: 232386 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.7428. Min Range: -0.7428

Max Act: 0.5425. Min Act: -0.0002

Data Index: 1318187 (C4 (Web Text))

Max Activating Token Index: 896