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

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

Neuron 5053 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.3017. Min Act: -0.0000

Data Index: 993252 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.2703. Min Act: -0.0000

Data Index: 534902 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1012103 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1311230 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1184860 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1322. Min Act: -0.0000

Data Index: 766995 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1956. Min Act: -0.0000

Data Index: 220470 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1455. Min Act: -0.0000

Data Index: 763954 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.2140. Min Act: -0.0001

Data Index: 664667 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1450. Min Act: -0.0000

Data Index: 140085 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0881. Min Act: -0.0000

Data Index: 181110 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1140074 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.1271. Min Act: -0.0000

Data Index: 263878 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0268. Min Act: -0.0000

Data Index: 306232 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0865. Min Act: -0.0000

Data Index: 835299 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0551. Min Act: -0.0000

Data Index: 919037 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0621. Min Act: -0.0000

Data Index: 800101 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0679. Min Act: -0.0000

Data Index: 962201 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0608. Min Act: -0.0001

Data Index: 1312751 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0568. Min Act: -0.0001

Data Index: 1335783 (C4 (Web Text))

Max Activating Token Index: 470