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

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

Neuron 4361 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5742. Min Range: -6.5742

Max Act: 6.5742. Min Act: -0.0001

Data Index: 727239 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.9154. Min Act: -0.0000

Data Index: 1277890 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.5299. Min Act: -0.0000

Data Index: 853285 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.9033. Min Act: -0.0000

Data Index: 747074 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.8794. Min Act: -0.0000

Data Index: 580547 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 6.5742. Min Range: -6.5742

Max Act: 6.2322. Min Act: -0.0000

Data Index: 1045614 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.9183. Min Act: -0.0000

Data Index: 1228703 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.8151. Min Act: -0.0000

Data Index: 1058652 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 6.5742. Min Range: -6.5742

Max Act: 6.0553. Min Act: -0.0000

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.6247. Min Act: -0.0001

Data Index: 1339388 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.2534. Min Act: -0.0001

Data Index: 1013812 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.7420. Min Act: -0.0000

Data Index: 654667 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.7832. Min Act: -0.0000

Data Index: 943407 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.9545. Min Act: -0.0001

Data Index: 508267 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.2435. Min Act: -0.0000

Data Index: 1133080 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.5653. Min Act: -0.0000

Data Index: 883090 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.5756. Min Act: -0.0000

Data Index: 861377 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.2521. Min Act: -0.0000

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.8863. Min Act: -0.0000

Data Index: 870811 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 6.5742. Min Range: -6.5742

Max Act: 5.5220. Min Act: -0.0000

Data Index: 326132 (C4 (Web Text))

Max Activating Token Index: 136