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

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

Neuron 733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.8406. Min Act: -0.0001

Data Index: 236165 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1133842 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.1077. Min Act: -0.0000

Data Index: 631331 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.0420. Min Act: -0.0000

Data Index: 105032 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.0493. Min Act: -0.0001

Data Index: 512672 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9793. Min Act: -0.0000

Data Index: 918528 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9576. Min Act: -0.0001

Data Index: 319497 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9524. Min Act: -0.0000

Data Index: 955026 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9227. Min Act: -0.0001

Data Index: 62130 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9515. Min Act: -0.0001

Data Index: 955180 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1186789 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9098. Min Act: -0.0001

Data Index: 375664 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1333583 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8841. Min Act: -0.0000

Data Index: 330531 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.9251. Min Act: -0.0001

Data Index: 903736 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8639. Min Act: -0.0001

Data Index: 519192 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1192518 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8476. Min Act: -0.0001

Data Index: 490311 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8154. Min Act: -0.0000

Data Index: 215632 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.8406. Min Range: -1.8406

Max Act: 0.8716. Min Act: -0.0001

Data Index: 93307 (C4 (Web Text))

Max Activating Token Index: 412