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

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

Neuron 2386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1302648 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6860. Min Act: -0.0001

Data Index: 106308 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6010. Min Act: -0.0001

Data Index: 447619 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6203. Min Act: -0.0001

Data Index: 530653 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5775. Min Act: -0.0001

Data Index: 130493 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5519. Min Act: -0.0001

Data Index: 46677 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5631. Min Act: -0.0001

Data Index: 726765 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1525511 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.7559. Min Act: -0.0001

Data Index: 612030 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6368. Min Act: -0.0001

Data Index: 1342842 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.4661. Min Act: -0.0001

Data Index: 874550 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1157748 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6512. Min Act: -0.0001

Data Index: 1071747 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5404. Min Act: -0.0001

Data Index: 897191 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5575. Min Act: -0.0001

Data Index: 559507 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6296. Min Act: -0.0001

Data Index: 6997 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.4547. Min Act: -0.0001

Data Index: 472897 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6075. Min Act: -0.0001

Data Index: 972840 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5567. Min Act: -0.0001

Data Index: 336856 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6220. Min Act: -0.0001

Data Index: 872520 (C4 (Web Text))

Max Activating Token Index: 865