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

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

Neuron 3076 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0222. Min Act: -0.0001

Data Index: 449723 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0001

Data Index: 61247 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1332677 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1184187 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 357706 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0201. Min Act: -0.0001

Data Index: 340226 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0199. Min Act: -0.0001

Data Index: 880686 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0200. Min Act: -0.0001

Data Index: 268574 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1325938 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0207. Min Act: -0.0001

Data Index: 432887 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0187. Min Act: -0.0001

Data Index: 604593 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0188. Min Act: -0.0001

Data Index: 326816 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1182874 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1091968 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0186. Min Act: -0.0001

Data Index: 719817 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0168. Min Act: -0.0001

Data Index: 541830 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0185. Min Act: -0.0001

Data Index: 889763 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1327306 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0192. Min Act: -0.0001

Data Index: 420131 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0187. Min Act: -0.0001

Data Index: 117931 (C4 (Web Text))

Max Activating Token Index: 576