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

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

Neuron 1092 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: 0.1498. Min Range: -0.1498

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1655188 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1498. Min Act: -0.0001

Data Index: 165761 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1395. Min Act: -0.0001

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1459969 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1323. Min Act: -0.0001

Data Index: 470865 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1451919 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1183. Min Act: -0.0001

Data Index: 376657 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1134278 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1522813 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1146. Min Act: -0.0001

Data Index: 313731 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1082. Min Act: -0.0001

Data Index: 428449 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1142. Min Act: -0.0001

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1641082 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1440748 (Python Code)

Max Activating Token Index: 254

Text #14

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1107. Min Act: -0.0001

Data Index: 528772 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1016. Min Act: -0.0001

Data Index: 993463 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1047. Min Act: -0.0001

Data Index: 54442 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1055. Min Act: -0.0001

Data Index: 337626 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1291126 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1070553 (C4 (Web Text))

Max Activating Token Index: 215