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

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

Neuron 5496 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.2964. Min Act: -0.0002

Data Index: 329447 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.2463. Min Act: -0.0003

Data Index: 730501 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.2557. Min Act: -0.0002

Data Index: 1306704 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1955. Min Act: -0.0003

Data Index: 286230 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1526. Min Act: -0.0003

Data Index: 675100 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1205. Min Act: -0.0002

Data Index: 1207952 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1234. Min Act: -0.0002

Data Index: 308865 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1154. Min Act: -0.0002

Data Index: 404777 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1296. Min Act: -0.0002

Data Index: 175960 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1138. Min Act: -0.0002

Data Index: 490452 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1062. Min Act: -0.0002

Data Index: 439581 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0928. Min Act: -0.0002

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1010. Min Act: -0.0002

Data Index: 239205 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0985. Min Act: -0.0002

Data Index: 687932 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.1124. Min Act: -0.0002

Data Index: 1326541 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0524. Min Act: -0.0003

Data Index: 2882 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0467. Min Act: -0.0003

Data Index: 169283 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0557. Min Act: -0.0002

Data Index: 437302 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0652. Min Act: -0.0002

Data Index: 927894 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.2964. Min Range: -1.2964

Max Act: 1.0357. Min Act: -0.0002

Data Index: 99080 (C4 (Web Text))

Max Activating Token Index: 408