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

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

Neuron 2763 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: 0.3761. Min Range: -0.3761

Max Act: 0.3761. Min Act: -0.0000

Data Index: 847702 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1032690 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2413. Min Act: -0.0001

Data Index: 573093 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2312. Min Act: -0.0001

Data Index: 70378 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2199. Min Act: -0.0001

Data Index: 499627 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2182. Min Act: -0.0001

Data Index: 914065 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2234. Min Act: -0.0000

Data Index: 764354 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1330796 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1214997 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2172. Min Act: -0.0001

Data Index: 169773 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2169. Min Act: -0.0000

Data Index: 354719 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1146696 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2090. Min Act: -0.0001

Data Index: 497606 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2020. Min Act: -0.0000

Data Index: 56116 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2001. Min Act: -0.0000

Data Index: 900122 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1909. Min Act: -0.0001

Data Index: 784273 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1114865 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1951. Min Act: -0.0001

Data Index: 578701 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1154357 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.1829. Min Act: -0.0001

Data Index: 545860 (C4 (Web Text))

Max Activating Token Index: 149