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

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

Neuron 268 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: 5.5729. Min Range: -5.5729

Max Act: 5.4363. Min Act: -0.0001

Data Index: 715963 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.5729. Min Range: -5.5729

Max Act: 5.1735. Min Act: -0.0001

Data Index: 434076 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 5.5729. Min Range: -5.5729

Max Act: 5.1109. Min Act: -0.0001

Data Index: 375297 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 5.5729. Min Range: -5.5729

Max Act: 5.5729. Min Act: -0.0001

Data Index: 268394 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.7664. Min Act: -0.0001

Data Index: 20675 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.7416. Min Act: -0.0001

Data Index: 820315 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.7586. Min Act: -0.0001

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.3958. Min Act: -0.0001

Data Index: 1207592 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 5.5729. Min Range: -5.5729

Max Act: 5.1116. Min Act: -0.0001

Data Index: 34879 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.5729. Min Range: -5.5729

Max Act: 5.3155. Min Act: -0.0001

Data Index: 679570 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.9024. Min Act: -0.0001

Data Index: 533965 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.8859. Min Act: -0.0001

Data Index: 180828 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.9786. Min Act: -0.0001

Data Index: 304658 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.6084. Min Act: -0.0001

Data Index: 672490 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.6711. Min Act: -0.0001

Data Index: 974101 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.6267. Min Act: -0.0001

Data Index: 443023 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.6002. Min Act: -0.0001

Data Index: 1243205 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.3861. Min Act: -0.0001

Data Index: 1319717 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.5647. Min Act: -0.0001

Data Index: 229627 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 5.5729. Min Range: -5.5729

Max Act: 4.3784. Min Act: -0.0001

Data Index: 863255 (C4 (Web Text))

Max Activating Token Index: 992