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

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

Neuron 1920 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3349. Min Act: -0.0000

Data Index: 477954 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1205818 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2475. Min Act: -0.0000

Data Index: 754976 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2430. Min Act: -0.0000

Data Index: 746300 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2401. Min Act: -0.0000

Data Index: 268237 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1191338 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2215. Min Act: -0.0000

Data Index: 308673 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2166. Min Act: -0.0000

Data Index: 662962 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2137. Min Act: -0.0000

Data Index: 894324 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2068. Min Act: -0.0000

Data Index: 631123 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2059. Min Act: -0.0000

Data Index: 387828 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1338737 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2188. Min Act: -0.0000

Data Index: 463491 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1251470 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2039. Min Act: -0.0000

Data Index: 905719 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2024. Min Act: -0.0000

Data Index: 290556 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1324653 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1894. Min Act: -0.0000

Data Index: 650038 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2025. Min Act: -0.0000

Data Index: 833362 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1357360 (C4 (Web Text))

Max Activating Token Index: 202