Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2511. Min Act: -0.0001

Data Index: 236391 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2287. Min Act: -0.0001

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2174. Min Act: -0.0001

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2221. Min Act: -0.0001

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2278. Min Act: -0.0001

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1121373 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2078. Min Act: -0.0001

Data Index: 958162 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2034. Min Act: -0.0000

Data Index: 773203 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2053. Min Act: -0.0001

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2167. Min Act: -0.0001

Data Index: 288436 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2048. Min Act: -0.0001

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1986. Min Act: -0.0001

Data Index: 336867 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1156899 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1993. Min Act: -0.0001

Data Index: 1136884 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2004. Min Act: -0.0001

Data Index: 149824 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1863. Min Act: -0.0001

Data Index: 140889 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2003. Min Act: -0.0001

Data Index: 104262 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1211415 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1908. Min Act: -0.0001

Data Index: 263697 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1110670 (C4 (Web Text))

Max Activating Token Index: 731