Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4936 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4429. Min Act: -0.0000

Data Index: 688358 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.4001. Min Act: -0.0000

Data Index: 270431 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3692. Min Act: -0.0000

Data Index: 44152 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1171366 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3207. Min Act: -0.0000

Data Index: 179945 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3345. Min Act: -0.0000

Data Index: 909098 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3335. Min Act: -0.0000

Data Index: 579557 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3210. Min Act: -0.0000

Data Index: 295221 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3474. Min Act: -0.0000

Data Index: 463401 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3299. Min Act: -0.0000

Data Index: 191782 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1301739 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3285. Min Act: -0.0000

Data Index: 232569 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3173. Min Act: -0.0000

Data Index: 4827 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.2748. Min Act: -0.0000

Data Index: 943481 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3241. Min Act: -0.0000

Data Index: 397734 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3003. Min Act: -0.0000

Data Index: 881024 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3092. Min Act: -0.0000

Data Index: 38733 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1154435 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1129648 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.4429. Min Range: -0.4429

Max Act: 0.3112. Min Act: -0.0000

Data Index: 615565 (C4 (Web Text))

Max Activating Token Index: 33