Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3369 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.4624. Min Range: -5.4624

Max Act: 5.4624. Min Act: -0.0001

Data Index: 344199 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.1087. Min Act: -0.0001

Data Index: 339102 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.4163. Min Act: -0.0001

Data Index: 458326 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.5339. Min Act: -0.0001

Data Index: 1330410 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.5323. Min Act: -0.0001

Data Index: 1009526 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.2126. Min Act: -0.0001

Data Index: 510415 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.3414. Min Act: -0.0001

Data Index: 871338 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.1391. Min Act: -0.0001

Data Index: 704278 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.9613. Min Act: -0.0001

Data Index: 179310 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.0433. Min Act: -0.0001

Data Index: 767905 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.1123. Min Act: -0.0001

Data Index: 69195 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.1165. Min Act: -0.0001

Data Index: 1120441 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.9505. Min Act: -0.0001

Data Index: 851251 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.7914. Min Act: -0.0001

Data Index: 1226116 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 5.4624. Min Range: -5.4624

Max Act: 3.1723. Min Act: -0.0001

Data Index: 168803 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.8852. Min Act: -0.0001

Data Index: 144579 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.7987. Min Act: -0.0001

Data Index: 22928 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.7490. Min Act: -0.0001

Data Index: 401509 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.2740. Min Act: -0.0001

Data Index: 1193665 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 5.4624. Min Range: -5.4624

Max Act: 2.7343. Min Act: -0.0001

Data Index: 827688 (C4 (Web Text))

Max Activating Token Index: 630