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

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

Neuron 630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2353. Min Act: -0.0002

Data Index: 1040678 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2193. Min Act: -0.0002

Data Index: 1015587 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1109785 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2250. Min Act: -0.0002

Data Index: 1287666 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2288. Min Act: -0.0002

Data Index: 845191 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2399. Min Act: -0.0001

Data Index: 175102 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2306. Min Act: -0.0002

Data Index: 695658 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2187. Min Act: -0.0002

Data Index: 138820 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2068. Min Act: -0.0002

Data Index: 285131 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1995. Min Act: -0.0001

Data Index: 68746 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2149. Min Act: -0.0002

Data Index: 1303954 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1102012 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2243. Min Act: -0.0001

Data Index: 943593 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1136071 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2150. Min Act: -0.0002

Data Index: 855175 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2234. Min Act: -0.0002

Data Index: 415066 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2205. Min Act: -0.0002

Data Index: 1322490 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2151. Min Act: -0.0002

Data Index: 177383 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2147. Min Act: -0.0002

Data Index: 204190 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2000. Min Act: -0.0001

Data Index: 846089 (C4 (Web Text))

Max Activating Token Index: 754