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

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

Neuron 2680 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: 2.6437. Min Range: -2.6437

Max Act: 2.6437. Min Act: -0.0000

Data Index: 706036 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.2683. Min Act: -0.0000

Data Index: 782721 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.1335. Min Act: -0.0000

Data Index: 1034918 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.1080. Min Act: -0.0000

Data Index: 1243902 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.0289. Min Act: -0.0000

Data Index: 858704 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.6437. Min Range: -2.6437

Max Act: 2.0098. Min Act: -0.0000

Data Index: 551665 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1315501 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.8507. Min Act: -0.0000

Data Index: 189629 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.8195. Min Act: -0.0000

Data Index: 278442 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.7419. Min Act: -0.0000

Data Index: 851160 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1130101 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.6775. Min Act: -0.0000

Data Index: 27158 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.7683. Min Act: -0.0000

Data Index: 151441 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.7142. Min Act: -0.0000

Data Index: 612251 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1007640 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.5691. Min Act: -0.0000

Data Index: 590864 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.4035. Min Act: -0.0000

Data Index: 354627 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.3647. Min Act: -0.0000

Data Index: 489034 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.6437. Min Range: -2.6437

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1210306 (C4 (Web Text))

Max Activating Token Index: 1023