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

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

Neuron 1376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2802. Min Act: -0.0000

Data Index: 234653 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2609. Min Act: -0.0000

Data Index: 419667 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2772. Min Act: -0.0000

Data Index: 470294 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1329480 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2738. Min Act: -0.0000

Data Index: 340183 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2502. Min Act: -0.0000

Data Index: 667359 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1128360 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2430. Min Act: -0.0000

Data Index: 856051 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2428. Min Act: -0.0000

Data Index: 390785 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1270470 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2304. Min Act: -0.0000

Data Index: 583815 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2355. Min Act: -0.0000

Data Index: 490534 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2358. Min Act: -0.0000

Data Index: 759090 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1023152 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2236. Min Act: -0.0000

Data Index: 440040 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2562. Min Act: -0.0000

Data Index: 16186 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2213. Min Act: -0.0000

Data Index: 911273 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1121324 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2083. Min Act: -0.0000

Data Index: 165973 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.2802. Min Range: -0.2802

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1119965 (C4 (Web Text))

Max Activating Token Index: 70