Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3685. Min Act: -0.0000

Data Index: 672693 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.3216. Min Act: -0.0000

Data Index: 769636 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2766. Min Act: -0.0000

Data Index: 310875 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2701. Min Act: -0.0000

Data Index: 174105 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2566. Min Act: -0.0000

Data Index: 502716 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2648. Min Act: -0.0000

Data Index: 142309 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1260473 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2305. Min Act: -0.0000

Data Index: 316421 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2433. Min Act: -0.0000

Data Index: 390339 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1106798 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2087. Min Act: -0.0000

Data Index: 346429 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1181921 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1139480 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2314. Min Act: -0.0000

Data Index: 420754 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2140. Min Act: -0.0000

Data Index: 700153 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2198. Min Act: -0.0000

Data Index: 792185 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2029. Min Act: -0.0000

Data Index: 656178 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2087. Min Act: -0.0001

Data Index: 52463 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.1820. Min Act: -0.0001

Data Index: 945298 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.3685. Min Range: -0.3685

Max Act: 0.2031. Min Act: -0.0000

Data Index: 275733 (C4 (Web Text))

Max Activating Token Index: 310