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

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

Neuron 4912 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6248. Min Act: -0.0000

Data Index: 179581 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6481. Min Act: -0.0000

Data Index: 976282 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6856. Min Act: -0.0000

Data Index: 20781 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1105130 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6399. Min Act: -0.0000

Data Index: 934435 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6656. Min Act: -0.0000

Data Index: 11422 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1159604 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0000

Data Index: 197042 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6184. Min Act: -0.0000

Data Index: 379104 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6581. Min Act: -0.0000

Data Index: 222634 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6909. Min Act: -0.0000

Data Index: 778461 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6553. Min Act: -0.0000

Data Index: 494863 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6501. Min Act: -0.0000

Data Index: 939975 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6359. Min Act: -0.0001

Data Index: 1281266 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6489. Min Act: -0.0001

Data Index: 910624 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6263. Min Act: -0.0000

Data Index: 946368 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6749. Min Act: -0.0000

Data Index: 979359 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1340139 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6306. Min Act: -0.0000

Data Index: 345084 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6112. Min Act: -0.0000

Data Index: 862654 (C4 (Web Text))

Max Activating Token Index: 570