Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3283 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0001

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1292. Min Act: -0.0001

Data Index: 143474 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1015280 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1185. Min Act: -0.0001

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1210. Min Act: -0.0001

Data Index: 885590 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1247. Min Act: -0.0001

Data Index: 548868 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1136. Min Act: -0.0001

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1138. Min Act: -0.0001

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1079. Min Act: -0.0000

Data Index: 185853 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1150. Min Act: -0.0001

Data Index: 960153 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1307433 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1066. Min Act: -0.0001

Data Index: 114182 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0971. Min Act: -0.0001

Data Index: 995094 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1044. Min Act: -0.0001

Data Index: 658058 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1062. Min Act: -0.0001

Data Index: 654309 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0981. Min Act: -0.0000

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0911. Min Act: -0.0001

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0981. Min Act: -0.0001

Data Index: 642019 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.0976. Min Act: -0.0001

Data Index: 699317 (C4 (Web Text))

Max Activating Token Index: 14