Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 192 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1234. Min Range: -2.1234

Max Act: 2.1234. Min Act: -0.0001

Data Index: 288344 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7530. Min Act: -0.0000

Data Index: 660414 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7251. Min Act: -0.0000

Data Index: 575043 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5243. Min Act: -0.0000

Data Index: 761364 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6491. Min Act: -0.0000

Data Index: 158821 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.8258. Min Act: -0.0000

Data Index: 719224 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5165. Min Act: -0.0000

Data Index: 950731 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1193574 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1082838 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4997. Min Act: -0.0001

Data Index: 994685 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.3703. Min Act: -0.0000

Data Index: 976946 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.3290. Min Act: -0.0000

Data Index: 260507 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4009. Min Act: -0.0000

Data Index: 200979 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4618. Min Act: -0.0000

Data Index: 648952 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1244793 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1331022 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.3433. Min Act: -0.0000

Data Index: 92619 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4161. Min Act: -0.0000

Data Index: 918997 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.3340. Min Act: -0.0001

Data Index: 143322 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1215469 (C4 (Web Text))

Max Activating Token Index: 382