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

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

Neuron 4399 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: 1.2350. Min Range: -1.2350

Max Act: 1.2350. Min Act: -0.0001

Data Index: 500905 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.2233. Min Act: -0.0001

Data Index: 409263 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.1500. Min Act: -0.0001

Data Index: 810247 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.1952. Min Act: -0.0001

Data Index: 868059 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.1221. Min Act: -0.0001

Data Index: 34358 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0523. Min Act: -0.0001

Data Index: 457996 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0810. Min Act: -0.0001

Data Index: 489669 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0883. Min Act: -0.0001

Data Index: 384528 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0224. Min Act: -0.0001

Data Index: 787645 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9869. Min Act: -0.0001

Data Index: 1085787 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0443. Min Act: -0.0001

Data Index: 295392 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9892. Min Act: -0.0001

Data Index: 1356504 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9841. Min Act: -0.0001

Data Index: 276689 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0415. Min Act: -0.0001

Data Index: 578293 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9956. Min Act: -0.0001

Data Index: 761655 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9699. Min Act: -0.0001

Data Index: 664769 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9867. Min Act: -0.0001

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9750. Min Act: -0.0001

Data Index: 603419 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8955. Min Act: -0.0001

Data Index: 116011 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0046. Min Act: -0.0001

Data Index: 383422 (C4 (Web Text))

Max Activating Token Index: 891