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

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

Neuron 503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.7439. Min Act: -0.0000

Data Index: 111851 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.4811. Min Act: -0.0000

Data Index: 356597 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.3922. Min Act: -0.0000

Data Index: 455291 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1147963 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2474. Min Act: -0.0000

Data Index: 906165 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.3395. Min Act: -0.0000

Data Index: 871557 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1107472 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.1702. Min Act: -0.0000

Data Index: 113341 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2923. Min Act: -0.0000

Data Index: 391567 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2685. Min Act: -0.0000

Data Index: 16953 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2474. Min Act: -0.0000

Data Index: 1345748 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2463. Min Act: -0.0000

Data Index: 452488 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.3602. Min Act: -0.0000

Data Index: 451047 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2444. Min Act: -0.0000

Data Index: 920092 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2419. Min Act: -0.0000

Data Index: 356316 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.0936. Min Act: -0.0000

Data Index: 644979 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2465. Min Act: -0.0000

Data Index: 329530 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2227. Min Act: -0.0000

Data Index: 392536 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2127. Min Act: -0.0000

Data Index: 1035782 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.7439. Min Range: -2.7439

Max Act: 2.2025. Min Act: -0.0000

Data Index: 345286 (C4 (Web Text))

Max Activating Token Index: 912