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

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

Neuron 2811 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6247. Min Range: -3.6247

Max Act: 3.2186. Min Act: -0.0000

Data Index: 908872 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.6247. Min Range: -3.6247

Max Act: 3.6247. Min Act: -0.0000

Data Index: 572819 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.8187. Min Act: -0.0000

Data Index: 202608 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.6247. Min Range: -3.6247

Max Act: 3.0408. Min Act: -0.0000

Data Index: 926620 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.6219. Min Act: -0.0000

Data Index: 1204623 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.6888. Min Act: -0.0000

Data Index: 239139 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.3211. Min Act: -0.0000

Data Index: 711988 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.4979. Min Act: -0.0000

Data Index: 1155502 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.2390. Min Act: -0.0000

Data Index: 623380 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.0200. Min Act: -0.0000

Data Index: 452580 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.6247. Min Range: -3.6247

Max Act: 1.9602. Min Act: -0.0000

Data Index: 121946 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.1358. Min Act: -0.0000

Data Index: 922625 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.2478. Min Act: -0.0000

Data Index: 619305 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.2081. Min Act: -0.0000

Data Index: 1065851 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.0390. Min Act: -0.0000

Data Index: 712353 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.6247. Min Range: -3.6247

Max Act: 2.0221. Min Act: -0.0000

Data Index: 724376 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.6247. Min Range: -3.6247

Max Act: 1.9843. Min Act: -0.0000

Data Index: 553023 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.6247. Min Range: -3.6247

Max Act: 1.8601. Min Act: -0.0000

Data Index: 506862 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 3.6247. Min Range: -3.6247

Max Act: 1.9303. Min Act: -0.0000

Data Index: 1042369 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.6247. Min Range: -3.6247

Max Act: 1.8257. Min Act: -0.0000

Data Index: 472561 (C4 (Web Text))

Max Activating Token Index: 764