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

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

Neuron 499 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.3001. Min Act: -0.0001

Data Index: 1116584 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.2551. Min Act: -0.0001

Data Index: 38910 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.1782. Min Act: -0.0001

Data Index: 282361 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0304. Min Act: -0.0001

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0915. Min Act: -0.0001

Data Index: 137062 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0944. Min Act: -0.0001

Data Index: 822168 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0268. Min Act: -0.0001

Data Index: 607861 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0817. Min Act: -0.0001

Data Index: 673974 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0868. Min Act: -0.0001

Data Index: 699595 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0523. Min Act: -0.0001

Data Index: 720144 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0860. Min Act: -0.0001

Data Index: 948639 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0628. Min Act: -0.0001

Data Index: 422134 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9336. Min Act: -0.0001

Data Index: 944663 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0145. Min Act: -0.0001

Data Index: 611803 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9510. Min Act: -0.0001

Data Index: 1267547 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.3001. Min Range: -1.3001

Max Act: 1.0033. Min Act: -0.0001

Data Index: 866022 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9907. Min Act: -0.0001

Data Index: 306769 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9852. Min Act: -0.0001

Data Index: 899214 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9739. Min Act: -0.0001

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.3001. Min Range: -1.3001

Max Act: 0.9803. Min Act: -0.0001

Data Index: 803675 (C4 (Web Text))

Max Activating Token Index: 370