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

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

Neuron 5012 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: 2.6326. Min Range: -2.6326

Max Act: 2.6326. Min Act: -0.0000

Data Index: 257748 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1203284 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.1407. Min Act: -0.0000

Data Index: 486449 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1101797 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.1538. Min Act: -0.0000

Data Index: 532838 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.1297. Min Act: -0.0000

Data Index: 1249236 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.0032. Min Act: -0.0000

Data Index: 996911 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9543. Min Act: -0.0000

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9294. Min Act: -0.0000

Data Index: 289563 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1181228 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9240. Min Act: -0.0000

Data Index: 634602 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9092. Min Act: -0.0000

Data Index: 112975 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.0077. Min Act: -0.0000

Data Index: 645133 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.0036. Min Act: -0.0000

Data Index: 670664 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 2.6326. Min Range: -2.6326

Max Act: 2.0590. Min Act: -0.0000

Data Index: 389478 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1161630 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1250187 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.9291. Min Act: -0.0000

Data Index: 622393 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1106505 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.6326. Min Range: -2.6326

Max Act: 1.6244. Min Act: -0.0000

Data Index: 233547 (C4 (Web Text))

Max Activating Token Index: 1021