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

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

Neuron 236 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: 2.9513. Min Range: -2.9513

Max Act: 2.7259. Min Act: -0.0000

Data Index: 1385272 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 2.9513. Min Range: -2.9513

Max Act: 2.9513. Min Act: 0.0000

Data Index: 1000912 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1392554 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.9448. Min Act: -0.0000

Data Index: 176069 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.5587. Min Act: 0.0000

Data Index: 992170 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1639120 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.8500. Min Act: -0.0000

Data Index: 403561 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.6162. Min Act: -0.0000

Data Index: 619332 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.6654. Min Act: 0.0001

Data Index: 1342700 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.5392. Min Act: 0.0000

Data Index: 1112578 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.4289. Min Act: -0.0000

Data Index: 796350 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.1610. Min Act: -0.0000

Data Index: 251415 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1089806 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.4512. Min Act: 0.0000

Data Index: 79520 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.2318. Min Act: -0.0000

Data Index: 997121 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1344398 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.4564. Min Act: -0.0000

Data Index: 989233 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.3891. Min Act: -0.0000

Data Index: 97443 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.2633. Min Act: -0.0000

Data Index: 643777 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.9513. Min Range: -2.9513

Max Act: 1.3035. Min Act: 0.0000

Data Index: 197978 (C4 (Web Text))

Max Activating Token Index: 365