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

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

Neuron 2701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.6063. Min Act: -0.0001

Data Index: 348369 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.5046. Min Act: -0.0001

Data Index: 991198 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4700. Min Act: -0.0001

Data Index: 761251 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4587. Min Act: -0.0001

Data Index: 43261 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4364. Min Act: -0.0001

Data Index: 1142674 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4388. Min Act: -0.0001

Data Index: 732079 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.4134. Min Act: -0.0001

Data Index: 397420 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3445. Min Act: -0.0001

Data Index: 136427 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3695. Min Act: -0.0001

Data Index: 1129198 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3350. Min Act: -0.0001

Data Index: 582142 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3500. Min Act: -0.0001

Data Index: 40588 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1211306 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3377. Min Act: -0.0001

Data Index: 81067 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3373. Min Act: -0.0001

Data Index: 741631 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3625. Min Act: -0.0001

Data Index: 285901 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3076. Min Act: -0.0001

Data Index: 36164 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3262. Min Act: -0.0001

Data Index: 408316 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3140. Min Act: -0.0001

Data Index: 157088 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1229795 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.6063. Min Range: -0.6063

Max Act: 0.3498. Min Act: -0.0001

Data Index: 457007 (C4 (Web Text))

Max Activating Token Index: 838