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

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

Neuron 1175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1574. Min Act: -0.0003

Data Index: 1309306 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0003

Data Index: 31957 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1561. Min Act: -0.0003

Data Index: 1356220 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1388. Min Act: -0.0003

Data Index: 1340812 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1320. Min Act: -0.0003

Data Index: 920884 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1349. Min Act: -0.0003

Data Index: 735740 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1355. Min Act: -0.0003

Data Index: 780530 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1086. Min Act: -0.0003

Data Index: 962877 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1301. Min Act: -0.0003

Data Index: 876429 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1180739 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1207. Min Act: -0.0003

Data Index: 405072 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1142. Min Act: -0.0003

Data Index: 813394 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1224. Min Act: -0.0003

Data Index: 132561 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1235. Min Act: -0.0003

Data Index: 531363 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1223. Min Act: -0.0003

Data Index: 1278331 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1183. Min Act: -0.0003

Data Index: 791403 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1212. Min Act: -0.0003

Data Index: 929369 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1203. Min Act: -0.0003

Data Index: 452983 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1194. Min Act: -0.0003

Data Index: 1350298 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1058. Min Act: -0.0003

Data Index: 65898 (C4 (Web Text))

Max Activating Token Index: 1009