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

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

Neuron 2916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5422. Min Act: -0.0001

Data Index: 112533 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5331. Min Act: -0.0000

Data Index: 285944 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5109. Min Act: -0.0000

Data Index: 553958 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5227. Min Act: -0.0001

Data Index: 270064 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1331836 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4876. Min Act: -0.0000

Data Index: 249444 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.5079. Min Act: -0.0000

Data Index: 843213 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4928. Min Act: -0.0000

Data Index: 409715 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4708. Min Act: -0.0001

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4824. Min Act: -0.0000

Data Index: 365985 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4653. Min Act: -0.0001

Data Index: 57000 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4850. Min Act: 0.0000

Data Index: 351111 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1074504 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4472. Min Act: -0.0001

Data Index: 920265 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4604. Min Act: -0.0000

Data Index: 12574 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1210208 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4668. Min Act: -0.0000

Data Index: 644863 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4333. Min Act: -0.0001

Data Index: 392398 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1014193 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.5422. Min Range: -0.5422

Max Act: 0.4263. Min Act: 0.0000

Data Index: 1127202 (C4 (Web Text))

Max Activating Token Index: 215