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

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

Neuron 3915 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.5110. Min Act: -0.0000

Data Index: 949572 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.2179. Min Act: -0.0000

Data Index: 153317 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.3291. Min Act: -0.0000

Data Index: 234851 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.2587. Min Act: -0.0000

Data Index: 1096917 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.0037. Min Act: -0.0000

Data Index: 758299 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.1077. Min Act: -0.0000

Data Index: 918170 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.2095. Min Act: -0.0000

Data Index: 672788 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.1018. Min Act: -0.0000

Data Index: 1211356 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.9907. Min Act: -0.0000

Data Index: 838092 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.0770. Min Act: -0.0000

Data Index: 928239 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.8557. Min Act: -0.0000

Data Index: 622342 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.9136. Min Act: -0.0000

Data Index: 1302874 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.9124. Min Act: -0.0000

Data Index: 1268241 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 2.5110. Min Range: -2.5110

Max Act: 2.0104. Min Act: -0.0000

Data Index: 299039 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.8803. Min Act: -0.0000

Data Index: 18622 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.7863. Min Act: -0.0000

Data Index: 1357146 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.9802. Min Act: -0.0000

Data Index: 648072 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.8773. Min Act: -0.0000

Data Index: 512469 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.9704. Min Act: -0.0000

Data Index: 373135 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 2.5110. Min Range: -2.5110

Max Act: 1.8508. Min Act: -0.0000

Data Index: 598021 (C4 (Web Text))

Max Activating Token Index: 291