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

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

Neuron 2702 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: 0.3063. Min Range: -0.3063

Max Act: 0.3063. Min Act: -0.0001

Data Index: 170320 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1320083 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2513. Min Act: -0.0001

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1227466 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1265744 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2752. Min Act: -0.0001

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2245. Min Act: -0.0001

Data Index: 540329 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2556. Min Act: -0.0001

Data Index: 637388 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2293. Min Act: -0.0001

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1006833 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2384. Min Act: -0.0001

Data Index: 380236 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2315. Min Act: -0.0001

Data Index: 230967 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2512. Min Act: -0.0001

Data Index: 913062 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2357. Min Act: -0.0001

Data Index: 167156 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2367. Min Act: -0.0001

Data Index: 12433 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2422. Min Act: -0.0001

Data Index: 669173 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2332. Min Act: -0.0001

Data Index: 637855 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1359538 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2275. Min Act: -0.0001

Data Index: 594778 (C4 (Web Text))

Max Activating Token Index: 881