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

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

Neuron 2221 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2866. Min Act: -0.0001

Data Index: 467734 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1015850 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2328. Min Act: -0.0001

Data Index: 78761 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1056506 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1103199 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2197. Min Act: -0.0001

Data Index: 1034030 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2317. Min Act: -0.0001

Data Index: 611376 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2277. Min Act: -0.0001

Data Index: 983357 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1208595 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2480. Min Act: -0.0001

Data Index: 982621 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2486. Min Act: -0.0001

Data Index: 647 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2143. Min Act: -0.0001

Data Index: 695697 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2106. Min Act: -0.0001

Data Index: 467532 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2397. Min Act: -0.0001

Data Index: 497749 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2051. Min Act: -0.0001

Data Index: 888623 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2298. Min Act: -0.0001

Data Index: 828734 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2184. Min Act: -0.0001

Data Index: 292480 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2078. Min Act: -0.0001

Data Index: 953144 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.1935. Min Act: -0.0001

Data Index: 496282 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.1899. Min Act: -0.0001

Data Index: 1032038 (C4 (Web Text))

Max Activating Token Index: 958