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

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

Neuron 2587 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: 4.4209. Min Range: -4.4209

Max Act: 4.2703. Min Act: -0.0001

Data Index: 884326 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 4.4209. Min Range: -4.4209

Max Act: 4.4209. Min Act: -0.0001

Data Index: 1228584 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 4.4209. Min Range: -4.4209

Max Act: 4.0024. Min Act: -0.0001

Data Index: 1279458 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 4.4209. Min Range: -4.4209

Max Act: 3.3910. Min Act: -0.0000

Data Index: 433843 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 4.4209. Min Range: -4.4209

Max Act: 3.3103. Min Act: -0.0001

Data Index: 2903 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 4.4209. Min Range: -4.4209

Max Act: 3.1432. Min Act: -0.0000

Data Index: 1195443 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.9325. Min Act: -0.0001

Data Index: 208798 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.9001. Min Act: -0.0001

Data Index: 46119 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.9319. Min Act: -0.0000

Data Index: 39162 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.7301. Min Act: -0.0000

Data Index: 1230568 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.3569. Min Act: -0.0001

Data Index: 1085908 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.4356. Min Act: -0.0000

Data Index: 1163612 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.2003. Min Act: -0.0000

Data Index: 155862 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.4161. Min Act: -0.0000

Data Index: 1328647 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.6218. Min Act: -0.0001

Data Index: 1155144 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.5058. Min Act: -0.0000

Data Index: 676778 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.6474. Min Act: -0.0000

Data Index: 306325 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.3078. Min Act: -0.0001

Data Index: 647388 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.3876. Min Act: -0.0000

Data Index: 491043 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 4.4209. Min Range: -4.4209

Max Act: 2.2204. Min Act: -0.0000

Data Index: 666515 (C4 (Web Text))

Max Activating Token Index: 394