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

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

Neuron 1339 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1190653 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1151165 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7553. Min Act: -0.0001

Data Index: 388447 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.7063. Min Act: -0.0001

Data Index: 932683 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6989. Min Act: -0.0001

Data Index: 300453 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6623. Min Act: -0.0001

Data Index: 874058 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6564. Min Act: -0.0001

Data Index: 52279 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6733. Min Act: -0.0001

Data Index: 625857 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6882. Min Act: -0.0001

Data Index: 492087 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6352. Min Act: -0.0001

Data Index: 479227 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.5977. Min Act: -0.0001

Data Index: 430788 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6528. Min Act: -0.0001

Data Index: 1236163 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6685. Min Act: -0.0001

Data Index: 1058870 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6441. Min Act: -0.0001

Data Index: 576903 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6183. Min Act: -0.0001

Data Index: 1312238 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6505. Min Act: -0.0001

Data Index: 965442 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6350. Min Act: -0.0001

Data Index: 93476 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6255. Min Act: -0.0001

Data Index: 263781 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6198. Min Act: -0.0001

Data Index: 1295599 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.9712. Min Range: -0.9712

Max Act: 0.6571. Min Act: -0.0001

Data Index: 20443 (C4 (Web Text))

Max Activating Token Index: 592