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

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

Neuron 4858 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: 0.9463. Min Range: -0.9463

Max Act: 0.9463. Min Act: -0.0003

Data Index: 657468 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8597. Min Act: -0.0003

Data Index: 1113196 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8798. Min Act: -0.0003

Data Index: 1091111 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8391. Min Act: -0.0002

Data Index: 841247 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8109. Min Act: -0.0003

Data Index: 358348 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8281. Min Act: -0.0003

Data Index: 204886 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7917. Min Act: -0.0003

Data Index: 681709 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8104. Min Act: -0.0003

Data Index: 1291148 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.8052. Min Act: -0.0003

Data Index: 25849 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7755. Min Act: -0.0003

Data Index: 1042076 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7733. Min Act: -0.0003

Data Index: 318381 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7809. Min Act: -0.0003

Data Index: 423713 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7988. Min Act: -0.0003

Data Index: 1162358 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7929. Min Act: -0.0002

Data Index: 471368 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7491. Min Act: -0.0003

Data Index: 61735 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7655. Min Act: -0.0003

Data Index: 743866 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7868. Min Act: -0.0003

Data Index: 940392 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7378. Min Act: -0.0002

Data Index: 242410 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7383. Min Act: -0.0003

Data Index: 393128 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.9463. Min Range: -0.9463

Max Act: 0.7556. Min Act: -0.0002

Data Index: 561809 (C4 (Web Text))

Max Activating Token Index: 594