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

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

Neuron 2000 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.7646. Min Act: -0.0000

Data Index: 133304 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1253901 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.7247. Min Act: 0.0000

Data Index: 580495 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6185. Min Act: -0.0000

Data Index: 607391 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6114. Min Act: -0.0000

Data Index: 666425 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6253. Min Act: -0.0000

Data Index: 64701 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1130023 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.6022. Min Act: 0.0000

Data Index: 222307 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1121248 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5921. Min Act: -0.0000

Data Index: 521692 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5884. Min Act: -0.0000

Data Index: 331628 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5976. Min Act: -0.0000

Data Index: 626054 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5420. Min Act: -0.0000

Data Index: 428145 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5363. Min Act: 0.0000

Data Index: 170946 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5478. Min Act: -0.0000

Data Index: 827134 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5818. Min Act: -0.0000

Data Index: 332675 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1269736 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1290669 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5310. Min Act: 0.0000

Data Index: 117047 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.7646. Min Range: -0.7646

Max Act: 0.5317. Min Act: -0.0000

Data Index: 108999 (C4 (Web Text))

Max Activating Token Index: 426