Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 994 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.2249. Min Act: -0.0001

Data Index: 807330 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.1725. Min Act: -0.0001

Data Index: 631204 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.1810. Min Act: -0.0001

Data Index: 931440 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.1484. Min Act: -0.0001

Data Index: 1298679 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9095. Min Act: -0.0001

Data Index: 736497 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0947. Min Act: -0.0001

Data Index: 1064589 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9837. Min Act: -0.0001

Data Index: 721310 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0056. Min Act: -0.0001

Data Index: 387159 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0006. Min Act: -0.0001

Data Index: 970823 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9135. Min Act: -0.0001

Data Index: 1097271 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9329. Min Act: -0.0001

Data Index: 463841 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9226. Min Act: -0.0001

Data Index: 218438 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9869. Min Act: -0.0001

Data Index: 351846 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9037. Min Act: -0.0001

Data Index: 840031 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.8293. Min Act: -0.0001

Data Index: 784091 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1220992 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.8883. Min Act: -0.0001

Data Index: 537475 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9241. Min Act: -0.0001

Data Index: 1070429 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.7147. Min Act: -0.0001

Data Index: 475567 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.8213. Min Act: -0.0001

Data Index: 373983 (C4 (Web Text))

Max Activating Token Index: 196