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

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

Neuron 1920 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.7149. Min Act: -0.0000

Data Index: 671247 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5599. Min Act: -0.0000

Data Index: 699860 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5146. Min Act: -0.0000

Data Index: 76877 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5217. Min Act: -0.0000

Data Index: 717062 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4763. Min Act: -0.0000

Data Index: 812465 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4581. Min Act: -0.0000

Data Index: 325836 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4432. Min Act: -0.0000

Data Index: 902950 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1266575 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4408. Min Act: -0.0000

Data Index: 964425 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4200. Min Act: -0.0000

Data Index: 436659 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4334. Min Act: -0.0000

Data Index: 651713 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1060475 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4232. Min Act: -0.0000

Data Index: 649667 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4048. Min Act: -0.0000

Data Index: 981835 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.5204. Min Act: -0.0000

Data Index: 802426 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4265. Min Act: -0.0000

Data Index: 505543 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4099. Min Act: -0.0000

Data Index: 908290 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.4066. Min Act: -0.0000

Data Index: 337125 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.3924. Min Act: -0.0000

Data Index: 770397 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.7149. Min Range: -0.7149

Max Act: 0.3831. Min Act: -0.0000

Data Index: 733706 (C4 (Web Text))

Max Activating Token Index: 580