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

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

Neuron 4583 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.8727. Min Act: -0.0000

Data Index: 928354 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1159026 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1012580 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7909. Min Act: -0.0000

Data Index: 702346 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7536. Min Act: -0.0000

Data Index: 133342 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7419. Min Act: -0.0000

Data Index: 801524 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7358. Min Act: -0.0000

Data Index: 948350 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1145199 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7262. Min Act: -0.0000

Data Index: 614161 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6997. Min Act: -0.0000

Data Index: 786286 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6911. Min Act: -0.0000

Data Index: 14925 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1286565 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1079962 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6643. Min Act: -0.0000

Data Index: 796033 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6366. Min Act: -0.0000

Data Index: 264365 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6683. Min Act: -0.0000

Data Index: 801568 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6889. Min Act: -0.0000

Data Index: 604956 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.7136. Min Act: -0.0000

Data Index: 375018 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6660. Min Act: -0.0000

Data Index: 890239 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.8727. Min Range: -0.8727

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1022274 (C4 (Web Text))

Max Activating Token Index: 971