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

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

Neuron 4702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1354490 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1124732 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6351. Min Act: -0.0000

Data Index: 293504 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6719. Min Act: -0.0000

Data Index: 164087 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1270159 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6135. Min Act: -0.0000

Data Index: 958997 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5723. Min Act: -0.0000

Data Index: 205213 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5740. Min Act: -0.0000

Data Index: 753760 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6016. Min Act: -0.0000

Data Index: 838616 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6244. Min Act: -0.0000

Data Index: 267494 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5466. Min Act: -0.0000

Data Index: 11244 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5565. Min Act: -0.0000

Data Index: 299051 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1119439 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5710. Min Act: -0.0000

Data Index: 49282 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5703. Min Act: -0.0000

Data Index: 513030 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5197. Min Act: -0.0000

Data Index: 768886 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5485. Min Act: -0.0000

Data Index: 904756 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5631. Min Act: -0.0000

Data Index: 954724 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5395. Min Act: -0.0000

Data Index: 16763 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1150820 (C4 (Web Text))

Max Activating Token Index: 250