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

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

Neuron 280 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2214. Min Act: -0.0001

Data Index: 607103 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1070237 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2051. Min Act: -0.0001

Data Index: 441420 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1318403 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2096. Min Act: -0.0001

Data Index: 426205 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1906. Min Act: -0.0001

Data Index: 143763 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1306. Min Act: -0.0001

Data Index: 300624 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1951. Min Act: -0.0001

Data Index: 818062 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1801. Min Act: -0.0001

Data Index: 862657 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1864. Min Act: -0.0001

Data Index: 20827 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1203. Min Act: -0.0001

Data Index: 501595 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1916. Min Act: -0.0001

Data Index: 77150 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1694. Min Act: -0.0001

Data Index: 728721 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1084913 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.2028. Min Act: -0.0001

Data Index: 947521 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1671. Min Act: -0.0001

Data Index: 548263 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1783. Min Act: -0.0001

Data Index: 407888 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1279. Min Act: -0.0001

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1648. Min Act: -0.0001

Data Index: 826 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.2214. Min Range: -0.2214

Max Act: 0.1619. Min Act: -0.0001

Data Index: 367587 (C4 (Web Text))

Max Activating Token Index: 850