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

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

Neuron 4716 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: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0000

Data Index: 355132 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1252573 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0471. Min Act: -0.0000

Data Index: 736978 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0433. Min Act: -0.0000

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0423. Min Act: -0.0000

Data Index: 923873 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0399. Min Act: -0.0000

Data Index: 402250 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0369. Min Act: -0.0000

Data Index: 865935 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0381. Min Act: -0.0000

Data Index: 973011 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0348. Min Act: -0.0000

Data Index: 147294 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0332. Min Act: -0.0000

Data Index: 899393 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0349. Min Act: -0.0000

Data Index: 724346 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1007999 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0362. Min Act: -0.0000

Data Index: 659197 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0356. Min Act: -0.0000

Data Index: 877717 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0354. Min Act: -0.0000

Data Index: 906083 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1176276 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0336. Min Act: -0.0000

Data Index: 281480 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0346. Min Act: -0.0000

Data Index: 547474 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0341. Min Act: -0.0000

Data Index: 10361 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0341. Min Act: -0.0000

Data Index: 388238 (C4 (Web Text))

Max Activating Token Index: 383