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

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

Neuron 773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.3168. Min Act: -0.0000

Data Index: 740507 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.2768. Min Act: -0.0000

Data Index: 881214 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1076052 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1374. Min Act: -0.0000

Data Index: 245992 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1986. Min Act: -0.0000

Data Index: 154711 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1004898 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1395. Min Act: -0.0000

Data Index: 840522 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1398. Min Act: -0.0000

Data Index: 117843 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1223530 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1241. Min Act: -0.0000

Data Index: 650744 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1216886 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0554. Min Act: -0.0000

Data Index: 519191 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1146. Min Act: -0.0000

Data Index: 600878 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0992. Min Act: -0.0000

Data Index: 75406 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1531405 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1015625 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.1050. Min Act: -0.0000

Data Index: 555059 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1036467 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0568. Min Act: -0.0000

Data Index: 780936 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.3168. Min Range: -1.3168

Max Act: 1.0701. Min Act: -0.0000

Data Index: 136776 (C4 (Web Text))

Max Activating Token Index: 759