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

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

Neuron 4008 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1283579 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1288982 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9615. Min Act: -0.0000

Data Index: 560907 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9499. Min Act: -0.0000

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.8260. Min Act: -0.0000

Data Index: 374835 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1217561 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7768. Min Act: -0.0000

Data Index: 206853 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.8018. Min Act: -0.0000

Data Index: 732451 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7712. Min Act: -0.0000

Data Index: 345040 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1305883 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7432. Min Act: -0.0000

Data Index: 476236 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.8090. Min Act: -0.0000

Data Index: 920025 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1291123 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7025. Min Act: -0.0000

Data Index: 47320 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7275. Min Act: -0.0000

Data Index: 778950 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7279. Min Act: -0.0000

Data Index: 590182 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.6678. Min Act: -0.0000

Data Index: 720686 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1292816 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.7098. Min Act: -0.0000

Data Index: 45152 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1004275 (C4 (Web Text))

Max Activating Token Index: 503