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

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

Neuron 2034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8562. Min Range: -7.8562

Max Act: 7.8562. Min Act: -0.0000

Data Index: 1116220 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 7.8562. Min Range: -7.8562

Max Act: 7.2257. Min Act: -0.0000

Data Index: 729812 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 7.8562. Min Range: -7.8562

Max Act: 7.1902. Min Act: -0.0000

Data Index: 562024 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 7.8562. Min Range: -7.8562

Max Act: 7.1425. Min Act: -0.0000

Data Index: 1243105 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 7.8562. Min Range: -7.8562

Max Act: 7.0738. Min Act: -0.0000

Data Index: 160902 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.7411. Min Act: -0.0000

Data Index: 1248650 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.5132. Min Act: -0.0000

Data Index: 576719 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.6844. Min Act: -0.0000

Data Index: 652719 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.6899. Min Act: -0.0000

Data Index: 818710 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.6090. Min Act: -0.0000

Data Index: 965082 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.2309. Min Act: -0.0000

Data Index: 339439 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.1938. Min Act: -0.0000

Data Index: 868353 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3628. Min Act: -0.0000

Data Index: 196700 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3319. Min Act: -0.0000

Data Index: 363564 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.6485. Min Act: -0.0000

Data Index: 422823 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3967. Min Act: -0.0000

Data Index: 233274 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3995. Min Act: -0.0000

Data Index: 1321564 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3896. Min Act: -0.0000

Data Index: 153043 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3565. Min Act: -0.0000

Data Index: 661306 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 7.8562. Min Range: -7.8562

Max Act: 6.3423. Min Act: -0.0000

Data Index: 1155295 (C4 (Web Text))

Max Activating Token Index: 44