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

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

Neuron 2511 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3958. Min Act: -0.0003

Data Index: 123436 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4445. Min Act: -0.0003

Data Index: 575835 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4010. Min Act: -0.0003

Data Index: 1009642 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4306. Min Act: -0.0003

Data Index: 501382 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3238. Min Act: -0.0003

Data Index: 852237 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2749. Min Act: -0.0003

Data Index: 151924 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2894. Min Act: -0.0003

Data Index: 51958 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2518. Min Act: -0.0003

Data Index: 784214 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9643. Min Act: -0.0003

Data Index: 1262756 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.3533. Min Act: -0.0003

Data Index: 902187 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2013. Min Act: -0.0003

Data Index: 1123100 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2336. Min Act: -0.0003

Data Index: 303028 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2695. Min Act: -0.0003

Data Index: 882710 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2246. Min Act: -0.0003

Data Index: 1198730 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1450. Min Act: -0.0003

Data Index: 810631 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2218. Min Act: -0.0003

Data Index: 1217235 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.0466. Min Act: -0.0003

Data Index: 792988 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9718. Min Act: -0.0003

Data Index: 169334 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2047. Min Act: -0.0003

Data Index: 558016 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1279. Min Act: -0.0004

Data Index: 133468 (C4 (Web Text))

Max Activating Token Index: 586