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

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

Neuron 722 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2390. Min Act: -0.0000

Data Index: 573625 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2588. Min Act: -0.0000

Data Index: 722469 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1069115 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2436. Min Act: -0.0000

Data Index: 567464 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2402. Min Act: -0.0000

Data Index: 489914 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2382. Min Act: -0.0000

Data Index: 952784 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2545. Min Act: -0.0000

Data Index: 939620 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2212. Min Act: -0.0000

Data Index: 381386 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1110506 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1259239 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1280756 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1093298 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1237094 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1079780 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.2019. Min Act: -0.0000

Data Index: 31403 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1885. Min Act: -0.0000

Data Index: 335385 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1922. Min Act: -0.0000

Data Index: 5311 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1836. Min Act: -0.0000

Data Index: 867703 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1953. Min Act: -0.0000

Data Index: 353068 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.2588. Min Range: -0.2588

Max Act: 0.1861. Min Act: -0.0000

Data Index: 876161 (C4 (Web Text))

Max Activating Token Index: 949