Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.2349. Min Act: -0.0000

Data Index: 713279 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.1048. Min Act: -0.0000

Data Index: 1306646 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0853. Min Act: -0.0000

Data Index: 1054493 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0459. Min Act: -0.0000

Data Index: 1123891 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.1498. Min Act: -0.0000

Data Index: 125115 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0328. Min Act: -0.0000

Data Index: 1084755 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.1192. Min Act: -0.0000

Data Index: 310907 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.1010. Min Act: -0.0000

Data Index: 228852 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1074226 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.1492. Min Act: -0.0000

Data Index: 944389 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0364. Min Act: -0.0000

Data Index: 685403 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0391. Min Act: -0.0000

Data Index: 1248203 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0296. Min Act: -0.0000

Data Index: 770113 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.2349. Min Range: -2.2349

Max Act: 2.0108. Min Act: -0.0000

Data Index: 246528 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.8936. Min Act: -0.0000

Data Index: 653348 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.9220. Min Act: -0.0000

Data Index: 1133261 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.9132. Min Act: -0.0000

Data Index: 408582 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.8091. Min Act: -0.0000

Data Index: 999340 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.7976. Min Act: -0.0000

Data Index: 214664 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.2349. Min Range: -2.2349

Max Act: 1.6867. Min Act: -0.0000

Data Index: 366976 (C4 (Web Text))

Max Activating Token Index: 307