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

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

Neuron 250 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.9188. Min Act: -0.0001

Data Index: 1158972 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.4862. Min Act: -0.0000

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.5683. Min Act: -0.0001

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.4741. Min Act: -0.0000

Data Index: 629072 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.4497. Min Act: -0.0000

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.4324. Min Act: -0.0001

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.3901. Min Act: -0.0000

Data Index: 908479 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2590. Min Act: -0.0001

Data Index: 1321757 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.4516. Min Act: -0.0000

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2044. Min Act: -0.0000

Data Index: 23700 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.3747. Min Act: -0.0000

Data Index: 127379 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2472. Min Act: -0.0001

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2536. Min Act: -0.0000

Data Index: 1266261 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.3618. Min Act: -0.0000

Data Index: 290131 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2274. Min Act: -0.0000

Data Index: 1118700 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.1631. Min Act: -0.0000

Data Index: 1096290 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2782. Min Act: -0.0000

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2505. Min Act: -0.0000

Data Index: 718589 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.2056. Min Act: -0.0000

Data Index: 951186 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.0751. Min Act: -0.0000

Data Index: 283723 (C4 (Web Text))

Max Activating Token Index: 795