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

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

Neuron 1518 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: 0.8511. Min Range: -0.8511

Max Act: 0.8511. Min Act: -0.0000

Data Index: 375863 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8192. Min Act: -0.0000

Data Index: 147005 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7039. Min Act: -0.0000

Data Index: 590043 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7276. Min Act: -0.0000

Data Index: 296863 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7144. Min Act: -0.0000

Data Index: 548837 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6977. Min Act: -0.0000

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1307673 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1354218 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7007. Min Act: -0.0000

Data Index: 625280 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1084465 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6320. Min Act: -0.0000

Data Index: 708484 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5897. Min Act: -0.0000

Data Index: 88256 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7066. Min Act: -0.0000

Data Index: 541225 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6224. Min Act: -0.0000

Data Index: 263187 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6239. Min Act: -0.0000

Data Index: 690486 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6201. Min Act: -0.0000

Data Index: 328788 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6005. Min Act: -0.0000

Data Index: 945656 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1213069 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5910. Min Act: -0.0000

Data Index: 86169 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1196059 (C4 (Web Text))

Max Activating Token Index: 268