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

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

Neuron 4590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0001

Data Index: 356179 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0330. Min Act: -0.0001

Data Index: 942895 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0325. Min Act: -0.0001

Data Index: 731579 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0266. Min Act: -0.0001

Data Index: 727158 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0277. Min Act: -0.0001

Data Index: 650687 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0265. Min Act: -0.0001

Data Index: 608575 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1015263 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0230. Min Act: -0.0001

Data Index: 693478 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0229. Min Act: -0.0001

Data Index: 562023 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1287770 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0223. Min Act: -0.0001

Data Index: 103642 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1225409 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1292000 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0206. Min Act: -0.0001

Data Index: 607349 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0203. Min Act: -0.0001

Data Index: 1341117 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0203. Min Act: -0.0001

Data Index: 460253 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1108772 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0189. Min Act: -0.0001

Data Index: 584191 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0189. Min Act: -0.0001

Data Index: 332488 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0187. Min Act: -0.0001

Data Index: 309436 (C4 (Web Text))

Max Activating Token Index: 216