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

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

Neuron 2394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1239. Min Act: -0.0000

Data Index: 780809 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1115809 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1179237 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1018. Min Act: -0.0001

Data Index: 705764 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1020. Min Act: -0.0001

Data Index: 506466 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0985. Min Act: -0.0001

Data Index: 979910 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1078778 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0978. Min Act: -0.0000

Data Index: 323585 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1064193 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0961. Min Act: -0.0000

Data Index: 547338 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1016. Min Act: -0.0001

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0959. Min Act: -0.0000

Data Index: 723734 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0942. Min Act: -0.0000

Data Index: 526641 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0913. Min Act: -0.0000

Data Index: 85464 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.1002. Min Act: -0.0001

Data Index: 281587 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0934. Min Act: 0.0000

Data Index: 471310 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0942. Min Act: -0.0000

Data Index: 286238 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1108924 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0875. Min Act: -0.0000

Data Index: 439061 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.1239. Min Range: -0.1239

Max Act: 0.0877. Min Act: -0.0000

Data Index: 624077 (C4 (Web Text))

Max Activating Token Index: 607