Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 641 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0367. Min Act: -0.0003

Data Index: 586422 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0003

Data Index: 784851 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0355. Min Act: -0.0003

Data Index: 184553 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1639425 (Python Code)

Max Activating Token Index: 625

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0277. Min Act: -0.0003

Data Index: 772244 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0328. Min Act: -0.0003

Data Index: 537274 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0326. Min Act: -0.0004

Data Index: 1520931 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1254697 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0298. Min Act: -0.0003

Data Index: 787060 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0318. Min Act: -0.0003

Data Index: 545910 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1202157 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0327. Min Act: -0.0003

Data Index: 817006 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0003

Data Index: 393344 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0284. Min Act: -0.0003

Data Index: 83007 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0317. Min Act: -0.0003

Data Index: 312942 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1559630 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1196870 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0303. Min Act: -0.0003

Data Index: 401267 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1308282 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1565424 (Python Code)

Max Activating Token Index: 102