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

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

Neuron 1152 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: 1.0173. Min Range: -1.0173

Max Act: 1.0173. Min Act: -0.0001

Data Index: 826101 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9802. Min Act: -0.0001

Data Index: 536966 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9203. Min Act: -0.0001

Data Index: 35928 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9346. Min Act: -0.0001

Data Index: 996832 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9489. Min Act: -0.0001

Data Index: 566857 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8649. Min Act: -0.0001

Data Index: 1245836 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8643. Min Act: -0.0001

Data Index: 545113 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8851. Min Act: -0.0001

Data Index: 390655 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8534. Min Act: -0.0001

Data Index: 677320 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8396. Min Act: -0.0001

Data Index: 948619 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8371. Min Act: -0.0001

Data Index: 948438 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9223. Min Act: -0.0001

Data Index: 12885 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1023854 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8531. Min Act: -0.0001

Data Index: 837949 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8454. Min Act: -0.0001

Data Index: 275019 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8241. Min Act: -0.0001

Data Index: 428481 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7895. Min Act: -0.0001

Data Index: 406745 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8738. Min Act: -0.0001

Data Index: 576564 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8415. Min Act: -0.0001

Data Index: 519591 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8471. Min Act: -0.0001

Data Index: 455138 (C4 (Web Text))

Max Activating Token Index: 474