Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1130 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5899. Min Act: -0.0002

Data Index: 605824 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.3903. Min Act: -0.0002

Data Index: 100206 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4094. Min Act: -0.0002

Data Index: 193315 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.3899. Min Act: -0.0002

Data Index: 258308 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.3269. Min Act: -0.0002

Data Index: 314254 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2727. Min Act: -0.0002

Data Index: 657755 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2896. Min Act: -0.0002

Data Index: 889010 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2877. Min Act: -0.0002

Data Index: 1006063 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2431. Min Act: -0.0002

Data Index: 784649 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2227. Min Act: -0.0002

Data Index: 542183 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2290. Min Act: -0.0002

Data Index: 179004 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.2254. Min Act: -0.0002

Data Index: 255862 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1896. Min Act: -0.0002

Data Index: 858589 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1880. Min Act: -0.0002

Data Index: 486246 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1886. Min Act: -0.0002

Data Index: 729358 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1836. Min Act: -0.0002

Data Index: 717324 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1557. Min Act: -0.0002

Data Index: 695553 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1699. Min Act: -0.0002

Data Index: 794521 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1574. Min Act: -0.0002

Data Index: 358692 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.1618. Min Act: -0.0003

Data Index: 123346 (C4 (Web Text))

Max Activating Token Index: 985