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

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

Neuron 4436 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: 1.0421. Min Range: -1.0421

Max Act: 1.0368. Min Act: -0.0001

Data Index: 1268726 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9553. Min Act: -0.0001

Data Index: 622884 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9910. Min Act: -0.0001

Data Index: 199446 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0421. Min Act: -0.0001

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.0421. Min Range: -1.0421

Max Act: 1.0262. Min Act: -0.0001

Data Index: 211366 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9692. Min Act: -0.0001

Data Index: 448550 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8158. Min Act: -0.0001

Data Index: 941804 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9486. Min Act: -0.0001

Data Index: 364230 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8969. Min Act: -0.0001

Data Index: 12691 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8918. Min Act: -0.0001

Data Index: 700543 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8764. Min Act: -0.0001

Data Index: 666235 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9113. Min Act: -0.0001

Data Index: 222442 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8875. Min Act: -0.0001

Data Index: 751191 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8796. Min Act: -0.0001

Data Index: 605304 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9171. Min Act: -0.0001

Data Index: 102358 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8358. Min Act: -0.0001

Data Index: 741897 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8540. Min Act: -0.0001

Data Index: 1237449 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8998. Min Act: -0.0001

Data Index: 931034 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.8482. Min Act: -0.0001

Data Index: 680295 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.0421. Min Range: -1.0421

Max Act: 0.9221. Min Act: -0.0001

Data Index: 956539 (C4 (Web Text))

Max Activating Token Index: 235