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

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

Neuron 1938 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: 0.7443. Min Range: -0.7443

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1065976 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.7271. Min Act: -0.0001

Data Index: 263512 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6688. Min Act: -0.0001

Data Index: 816479 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1135371 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6811. Min Act: -0.0001

Data Index: 202859 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6552. Min Act: -0.0001

Data Index: 892636 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1155960 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6798. Min Act: -0.0001

Data Index: 740671 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6368. Min Act: -0.0001

Data Index: 766446 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6775. Min Act: -0.0001

Data Index: 59338 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1044548 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6594. Min Act: -0.0001

Data Index: 21431 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1101705 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.5755. Min Act: -0.0001

Data Index: 367759 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6294. Min Act: -0.0001

Data Index: 690841 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6458. Min Act: -0.0001

Data Index: 823745 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6082. Min Act: -0.0001

Data Index: 614865 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6446. Min Act: -0.0001

Data Index: 928766 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6616. Min Act: -0.0001

Data Index: 448089 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.7443. Min Range: -0.7443

Max Act: 0.6451. Min Act: -0.0001

Data Index: 1033335 (C4 (Web Text))

Max Activating Token Index: 156