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

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

Neuron 1678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.2288. Min Act: -0.0001

Data Index: 224656 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1032576 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.2019. Min Act: -0.0001

Data Index: 874929 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1313778 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.2042. Min Act: -0.0001

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1151501 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1590. Min Act: -0.0001

Data Index: 539179 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1390. Min Act: -0.0001

Data Index: 492101 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1300. Min Act: -0.0001

Data Index: 123950 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1512. Min Act: -0.0001

Data Index: 304032 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1129561 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1188. Min Act: -0.0001

Data Index: 231188 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1271. Min Act: -0.0001

Data Index: 880755 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1013. Min Act: -0.0001

Data Index: 790109 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1102884 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1079. Min Act: -0.0001

Data Index: 22035 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.0992. Min Act: -0.0001

Data Index: 763394 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.0975. Min Act: -0.0001

Data Index: 777480 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1064. Min Act: -0.0001

Data Index: 308664 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.2288. Min Range: -0.2288

Max Act: 0.1008. Min Act: -0.0001

Data Index: 431926 (C4 (Web Text))

Max Activating Token Index: 12