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

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

Neuron 4890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8352. Min Act: -0.0001

Data Index: 751790 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.0033. Min Range: -1.0033

Max Act: 1.0033. Min Act: -0.0001

Data Index: 548110 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.9761. Min Act: -0.0001

Data Index: 458403 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.9230. Min Act: -0.0001

Data Index: 996846 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8774. Min Act: -0.0001

Data Index: 1269251 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8331. Min Act: -0.0001

Data Index: 311837 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8592. Min Act: -0.0001

Data Index: 83259 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8235. Min Act: -0.0001

Data Index: 106522 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8364. Min Act: -0.0001

Data Index: 689409 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8502. Min Act: -0.0001

Data Index: 929635 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8022. Min Act: -0.0001

Data Index: 762373 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8150. Min Act: -0.0001

Data Index: 667790 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7649. Min Act: -0.0001

Data Index: 578232 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7749. Min Act: -0.0001

Data Index: 451262 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1044924 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7519. Min Act: -0.0001

Data Index: 45021 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8199. Min Act: -0.0001

Data Index: 1334949 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1249742 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7705. Min Act: -0.0001

Data Index: 668967 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6805. Min Act: -0.0001

Data Index: 201341 (C4 (Web Text))

Max Activating Token Index: 646