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

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

Neuron 4985 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1110385 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0844. Min Act: -0.0000

Data Index: 848477 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0385. Min Act: -0.0000

Data Index: 622719 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0283. Min Act: -0.0000

Data Index: 383160 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0093. Min Act: -0.0000

Data Index: 170235 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1319284 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9977. Min Act: -0.0000

Data Index: 299258 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9657. Min Act: -0.0000

Data Index: 229685 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9488. Min Act: -0.0000

Data Index: 852910 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9373. Min Act: -0.0000

Data Index: 903626 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9478. Min Act: -0.0000

Data Index: 442982 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8825. Min Act: -0.0000

Data Index: 494274 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8586. Min Act: -0.0000

Data Index: 260851 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9381. Min Act: -0.0000

Data Index: 132441 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8448. Min Act: -0.0000

Data Index: 408264 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1213724 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8668. Min Act: -0.0000

Data Index: 391386 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1187422 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8164. Min Act: -0.0000

Data Index: 164517 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1084807 (C4 (Web Text))

Max Activating Token Index: 696