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

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

Neuron 1700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.6545. Min Act: -0.0000

Data Index: 905666 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.6182. Min Act: -0.0000

Data Index: 878993 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5625. Min Act: 0.0003

Data Index: 499148 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5369. Min Act: -0.0000

Data Index: 732564 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1217266 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5281. Min Act: 0.0000

Data Index: 556568 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4973. Min Act: -0.0000

Data Index: 607661 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5149. Min Act: -0.0000

Data Index: 740612 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5162. Min Act: -0.0000

Data Index: 149637 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4755. Min Act: -0.0000

Data Index: 336925 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4546. Min Act: -0.0000

Data Index: 13558 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1149927 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4553. Min Act: 0.0000

Data Index: 129690 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4459. Min Act: -0.0000

Data Index: 546617 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1177692 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4520. Min Act: -0.0001

Data Index: 394095 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1129080 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4370. Min Act: -0.0000

Data Index: 968794 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4488. Min Act: -0.0000

Data Index: 275266 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4337. Min Act: -0.0001

Data Index: 857522 (C4 (Web Text))

Max Activating Token Index: 952