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

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

Neuron 5747 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2411. Min Act: -0.0000

Data Index: 257217 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.4199. Min Act: -0.0000

Data Index: 693456 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2471. Min Act: -0.0000

Data Index: 1114205 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2250. Min Act: -0.0000

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2780. Min Act: -0.0000

Data Index: 548372 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.0674. Min Act: -0.0000

Data Index: 792824 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2051. Min Act: -0.0000

Data Index: 964543 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2178. Min Act: -0.0000

Data Index: 329358 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.1041. Min Act: -0.0000

Data Index: 436373 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2708. Min Act: -0.0000

Data Index: 234271 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.0822. Min Act: -0.0000

Data Index: 496413 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2214. Min Act: -0.0000

Data Index: 939685 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.0405. Min Act: -0.0000

Data Index: 402754 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.2231. Min Act: -0.0000

Data Index: 1249437 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.3378. Min Act: -0.0000

Data Index: 954950 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 4.4199. Min Range: -4.4199

Max Act: 4.1904. Min Act: -0.0000

Data Index: 1039620 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 4.4199. Min Range: -4.4199

Max Act: 3.8039. Min Act: -0.0000

Data Index: 1241710 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 4.4199. Min Range: -4.4199

Max Act: 3.7571. Min Act: -0.0000

Data Index: 56330 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 4.4199. Min Range: -4.4199

Max Act: 3.5916. Min Act: -0.0000

Data Index: 923996 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 4.4199. Min Range: -4.4199

Max Act: 3.5155. Min Act: -0.0000

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 929