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

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

Neuron 4908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.6630. Min Act: -0.0000

Data Index: 921865 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.3747. Min Act: -0.0000

Data Index: 622570 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.6418. Min Act: -0.0000

Data Index: 154244 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.6244. Min Act: -0.0000

Data Index: 800942 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.4676. Min Act: -0.0000

Data Index: 788859 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.3534. Min Act: -0.0000

Data Index: 239954 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.6422. Min Act: -0.0000

Data Index: 949280 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.2187. Min Act: -0.0000

Data Index: 281992 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.4297. Min Act: -0.0000

Data Index: 1306183 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.1124. Min Act: -0.0000

Data Index: 1216586 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.0429. Min Act: -0.0000

Data Index: 419105 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.2470. Min Act: -0.0000

Data Index: 232078 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.0860. Min Act: -0.0000

Data Index: 896988 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.6630. Min Range: -2.6630

Max Act: 1.9534. Min Act: -0.0000

Data Index: 553895 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.0353. Min Act: -0.0000

Data Index: 26736 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.1396. Min Act: -0.0000

Data Index: 975816 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.1223. Min Act: -0.0000

Data Index: 256020 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.0330. Min Act: -0.0000

Data Index: 850773 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 2.6630. Min Range: -2.6630

Max Act: 2.1197. Min Act: -0.0000

Data Index: 823465 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 2.6630. Min Range: -2.6630

Max Act: 1.9046. Min Act: -0.0000

Data Index: 190427 (C4 (Web Text))

Max Activating Token Index: 148