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

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

Neuron 3989 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.8045. Min Act: 0.0000

Data Index: 1201644 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.6734. Min Act: -0.0000

Data Index: 1244161 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.5298. Min Act: -0.0000

Data Index: 235226 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.4206. Min Act: -0.0000

Data Index: 311816 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.4142. Min Act: -0.0000

Data Index: 734179 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1059525 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.4131. Min Act: -0.0000

Data Index: 728480 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.3046. Min Act: -0.0000

Data Index: 461945 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.3497. Min Act: -0.0000

Data Index: 456481 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1339587 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.3143. Min Act: -0.0000

Data Index: 772489 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1237234 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.2148. Min Act: -0.0000

Data Index: 55360 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.2299. Min Act: -0.0000

Data Index: 735639 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.1453. Min Act: -0.0000

Data Index: 471615 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.0746. Min Act: -0.0000

Data Index: 521631 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.1961. Min Act: -0.0000

Data Index: 245747 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.2548. Min Act: -0.0000

Data Index: 635080 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.2428. Min Act: 0.0000

Data Index: 660090 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.8045. Min Range: -1.8045

Max Act: 1.1651. Min Act: -0.0000

Data Index: 731012 (C4 (Web Text))

Max Activating Token Index: 684