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

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

Neuron 5060 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: 3.8864. Min Range: -3.8864

Max Act: 3.8864. Min Act: -0.0000

Data Index: 532561 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.8196. Min Act: -0.0000

Data Index: 722738 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.4760. Min Act: -0.0000

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.3347. Min Act: -0.0000

Data Index: 96535 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.3287. Min Act: -0.0000

Data Index: 50466 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.1835. Min Act: -0.0000

Data Index: 1221464 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.3233. Min Act: -0.0000

Data Index: 795120 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.2716. Min Act: -0.0000

Data Index: 1155737 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.1950. Min Act: -0.0000

Data Index: 439560 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.1410. Min Act: -0.0000

Data Index: 131113 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.1421. Min Act: -0.0000

Data Index: 333349 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.9955. Min Act: -0.0000

Data Index: 387395 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 3.8864. Min Range: -3.8864

Max Act: 3.0019. Min Act: -0.0000

Data Index: 1130261 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.7723. Min Act: -0.0000

Data Index: 1217347 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.8330. Min Act: -0.0000

Data Index: 470569 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.8367. Min Act: -0.0000

Data Index: 1006779 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.6878. Min Act: -0.0000

Data Index: 1104212 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.4650. Min Act: -0.0000

Data Index: 886127 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.6632. Min Act: -0.0000

Data Index: 677996 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.8864. Min Range: -3.8864

Max Act: 2.3949. Min Act: -0.0000

Data Index: 103849 (C4 (Web Text))

Max Activating Token Index: 774