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

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

Neuron 3352 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1628. Min Act: -0.0000

Data Index: 601115 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1221924 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8592. Min Act: -0.0000

Data Index: 14273 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1247866 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7813. Min Act: -0.0001

Data Index: 469789 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1099988 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7676. Min Act: -0.0000

Data Index: 645436 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6911. Min Act: -0.0000

Data Index: 314556 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7352. Min Act: -0.0001

Data Index: 433350 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1041378 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1346501 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6834. Min Act: -0.0001

Data Index: 658416 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6620. Min Act: -0.0001

Data Index: 969084 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7260. Min Act: -0.0001

Data Index: 864238 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7069. Min Act: -0.0000

Data Index: 931859 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6589. Min Act: -0.0000

Data Index: 172326 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7107. Min Act: -0.0000

Data Index: 379380 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6917. Min Act: -0.0001

Data Index: 247164 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6915. Min Act: -0.0000

Data Index: 748313 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6836. Min Act: -0.0000

Data Index: 50362 (C4 (Web Text))

Max Activating Token Index: 851