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

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

Neuron 1780 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2791. Min Act: 0.0000

Data Index: 1193785 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1510293 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1508358 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2298. Min Act: 0.0000

Data Index: 907715 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2259. Min Act: -0.0000

Data Index: 454449 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1053394 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1604562 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1299146 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2156. Min Act: 0.0000

Data Index: 968675 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2004. Min Act: -0.0000

Data Index: 360444 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2125. Min Act: 0.0001

Data Index: 186993 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1394901 (Python Code)

Max Activating Token Index: 870

Text #12

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1424914 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1440841 (Python Code)

Max Activating Token Index: 210

Text #14

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1233582 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1970. Min Act: 0.0000

Data Index: 554782 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1982. Min Act: 0.0000

Data Index: 288935 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1982. Min Act: 0.0000

Data Index: 234499 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1882. Min Act: -0.0000

Data Index: 981376 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1471608 (Python Code)

Max Activating Token Index: 54