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

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

Neuron 2994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1338. Min Range: -2.1338

Max Act: 2.1338. Min Act: -0.0000

Data Index: 730606 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.9883. Min Act: -0.0000

Data Index: 283767 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.9134. Min Act: -0.0000

Data Index: 437149 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6803. Min Act: -0.0000

Data Index: 521678 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6342. Min Act: -0.0000

Data Index: 431332 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.7039. Min Act: -0.0000

Data Index: 1031307 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1181160 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6391. Min Act: -0.0000

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6092. Min Act: -0.0000

Data Index: 705380 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.6034. Min Act: -0.0000

Data Index: 324307 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1216736 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.5805. Min Act: -0.0000

Data Index: 432752 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.5034. Min Act: -0.0000

Data Index: 197334 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4505. Min Act: -0.0000

Data Index: 741350 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4697. Min Act: -0.0000

Data Index: 428684 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4182. Min Act: -0.0000

Data Index: 169624 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1053993 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4160. Min Act: -0.0000

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.1338. Min Range: -2.1338

Max Act: 1.4703. Min Act: -0.0000

Data Index: 18189 (C4 (Web Text))

Max Activating Token Index: 1008