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

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

Neuron 2769 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1267. Min Act: -0.0001

Data Index: 423758 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1256. Min Act: -0.0001

Data Index: 490844 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1328. Min Act: -0.0001

Data Index: 897370 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1275828 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1004926 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1167188 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1081. Min Act: -0.0001

Data Index: 52952 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1256. Min Act: -0.0001

Data Index: 518569 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1143. Min Act: -0.0001

Data Index: 961704 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1588308 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1452941 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1561555 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1518946 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1403508 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1164. Min Act: -0.0001

Data Index: 547284 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1366. Min Act: -0.0001

Data Index: 132553 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1082. Min Act: -0.0001

Data Index: 546118 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1062. Min Act: -0.0001

Data Index: 88918 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1307329 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.1446. Min Range: -0.1446

Max Act: 0.1214. Min Act: -0.0001

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 91