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

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

Neuron 336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.2006. Min Act: -0.0001

Data Index: 260508 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.1404. Min Act: -0.0001

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8808. Min Act: -0.0001

Data Index: 992094 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0111. Min Act: -0.0001

Data Index: 325059 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1157524 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9839. Min Act: -0.0001

Data Index: 1173268 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9383. Min Act: -0.0001

Data Index: 352860 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9191. Min Act: -0.0001

Data Index: 1210701 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9353. Min Act: -0.0001

Data Index: 591797 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9164. Min Act: -0.0001

Data Index: 1229236 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8839. Min Act: -0.0001

Data Index: 920227 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9273. Min Act: -0.0001

Data Index: 374376 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8975. Min Act: -0.0001

Data Index: 964739 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8695. Min Act: -0.0001

Data Index: 599987 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8348. Min Act: -0.0001

Data Index: 421733 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8641. Min Act: -0.0001

Data Index: 625535 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8754. Min Act: -0.0001

Data Index: 546388 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1356554 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1142027 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8466. Min Act: -0.0001

Data Index: 230495 (C4 (Web Text))

Max Activating Token Index: 26