Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2371 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5179. Min Act: -0.0000

Data Index: 925698 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4926. Min Act: -0.0000

Data Index: 766466 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5216. Min Act: -0.0000

Data Index: 165849 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5190. Min Act: -0.0000

Data Index: 621829 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1317456 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1137186 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4475. Min Act: -0.0000

Data Index: 88703 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4510. Min Act: -0.0000

Data Index: 685877 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4178. Min Act: -0.0000

Data Index: 249807 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4315. Min Act: -0.0000

Data Index: 473625 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4429. Min Act: -0.0000

Data Index: 941072 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4222. Min Act: -0.0000

Data Index: 417247 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4156. Min Act: 0.0000

Data Index: 64182 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4081. Min Act: -0.0000

Data Index: 757364 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3878. Min Act: 0.0001

Data Index: 898119 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1022522 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3883. Min Act: 0.0001

Data Index: 1197093 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1042416 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3875. Min Act: -0.0000

Data Index: 255972 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.3842. Min Act: 0.0001

Data Index: 1323460 (C4 (Web Text))

Max Activating Token Index: 684