Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0006

Data Index: 73082 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0202. Min Act: -0.0006

Data Index: 230343 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0193. Min Act: -0.0006

Data Index: 12270 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1290071 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0183. Min Act: -0.0006

Data Index: 361996 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1265251 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0181. Min Act: -0.0006

Data Index: 244841 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 550378 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 790904 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1191386 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0175. Min Act: -0.0006

Data Index: 392609 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0170. Min Act: -0.0006

Data Index: 213807 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1033708 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1267544 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0171. Min Act: -0.0006

Data Index: 287692 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0171. Min Act: -0.0006

Data Index: 126860 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1171316 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0163. Min Act: -0.0006

Data Index: 948522 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0173. Min Act: -0.0006

Data Index: 237223 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0179. Min Act: -0.0006

Data Index: 493393 (C4 (Web Text))

Max Activating Token Index: 650