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

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

Neuron 1834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.4123. Min Act: 0.0000

Data Index: 628324 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1207426 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.1828. Min Act: -0.0000

Data Index: 144766 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.1282. Min Act: -0.0000

Data Index: 330161 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.0972. Min Act: -0.0000

Data Index: 324711 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9847. Min Act: -0.0000

Data Index: 344687 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.0431. Min Act: -0.0000

Data Index: 970550 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.4123. Min Range: -1.4123

Max Act: 1.0147. Min Act: -0.0000

Data Index: 284951 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9805. Min Act: -0.0000

Data Index: 879177 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1216769 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9367. Min Act: -0.0000

Data Index: 117402 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9399. Min Act: -0.0000

Data Index: 289211 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9599. Min Act: -0.0000

Data Index: 722122 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1308371 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9506. Min Act: -0.0000

Data Index: 369253 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9167. Min Act: -0.0000

Data Index: 110321 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9454. Min Act: -0.0000

Data Index: 285741 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1273515 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.4123. Min Range: -1.4123

Max Act: 0.9283. Min Act: -0.0000

Data Index: 998604 (C4 (Web Text))

Max Activating Token Index: 337