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

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

Neuron 4315 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 708149 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6978. Min Act: -0.0000

Data Index: 482865 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5514. Min Act: -0.0000

Data Index: 580078 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5632. Min Act: -0.0000

Data Index: 811395 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5539. Min Act: -0.0000

Data Index: 219566 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5165. Min Act: -0.0000

Data Index: 399388 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5821. Min Act: -0.0000

Data Index: 996687 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5640. Min Act: -0.0000

Data Index: 500793 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1143275 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5293. Min Act: -0.0000

Data Index: 430671 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5459. Min Act: -0.0000

Data Index: 18548 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4906. Min Act: -0.0000

Data Index: 258018 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1302503 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1256734 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4983. Min Act: -0.0000

Data Index: 131532 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.5302. Min Act: -0.0000

Data Index: 390160 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1165260 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4269. Min Act: -0.0000

Data Index: 761186 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.3814. Min Act: -0.0000

Data Index: 266714 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.4390. Min Act: -0.0000

Data Index: 566675 (C4 (Web Text))

Max Activating Token Index: 666