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

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

Neuron 2450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8503. Min Act: -0.0001

Data Index: 486671 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1052478 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6297. Min Act: -0.0001

Data Index: 595699 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1107174 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6056. Min Act: -0.0001

Data Index: 1318647 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6095. Min Act: -0.0001

Data Index: 724470 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6065. Min Act: -0.0000

Data Index: 833871 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5673. Min Act: -0.0001

Data Index: 930553 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5461. Min Act: -0.0001

Data Index: 161984 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5709. Min Act: -0.0001

Data Index: 958194 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5295. Min Act: -0.0001

Data Index: 583152 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1207837 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4902. Min Act: -0.0000

Data Index: 242323 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4692. Min Act: -0.0001

Data Index: 400709 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5877. Min Act: -0.0001

Data Index: 336646 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1010473 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4202. Min Act: -0.0001

Data Index: 874435 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4557. Min Act: -0.0001

Data Index: 685451 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.4398. Min Act: -0.0000

Data Index: 102234 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.3903. Min Act: -0.0001

Data Index: 558480 (C4 (Web Text))

Max Activating Token Index: 69