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

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

Neuron 5356 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: 1.4258. Min Range: -1.4258

Max Act: 1.4126. Min Act: -0.0001

Data Index: 774641 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1247903 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2073. Min Act: -0.0000

Data Index: 249178 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2318. Min Act: -0.0000

Data Index: 464345 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2116. Min Act: -0.0001

Data Index: 842373 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.0357. Min Act: -0.0001

Data Index: 72011 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2724. Min Act: -0.0000

Data Index: 365744 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2060. Min Act: -0.0000

Data Index: 28084 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1514. Min Act: -0.0001

Data Index: 338134 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1559. Min Act: -0.0000

Data Index: 444258 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1133858 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1247. Min Act: -0.0001

Data Index: 411921 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.0826. Min Act: -0.0000

Data Index: 917624 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1208. Min Act: -0.0001

Data Index: 607408 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1177261 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1103335 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.2233. Min Act: -0.0000

Data Index: 347456 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1094. Min Act: -0.0001

Data Index: 594160 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.1064. Min Act: -0.0001

Data Index: 737575 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.4258. Min Range: -1.4258

Max Act: 1.0664. Min Act: -0.0001

Data Index: 1336250 (C4 (Web Text))

Max Activating Token Index: 622