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

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

Neuron 2422 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: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0003

Data Index: 256665 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1414. Min Act: -0.0003

Data Index: 800850 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1498. Min Act: -0.0003

Data Index: 474256 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1361. Min Act: -0.0003

Data Index: 1220540 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1260. Min Act: -0.0003

Data Index: 1276717 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1310. Min Act: -0.0003

Data Index: 783201 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1263. Min Act: -0.0003

Data Index: 1085487 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1193. Min Act: -0.0003

Data Index: 981867 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1232. Min Act: -0.0003

Data Index: 341924 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1037649 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1196. Min Act: -0.0003

Data Index: 944057 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1067. Min Act: -0.0003

Data Index: 360000 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1104. Min Act: -0.0003

Data Index: 556217 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1142. Min Act: -0.0003

Data Index: 684608 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1185. Min Act: -0.0003

Data Index: 1123375 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1216. Min Act: -0.0003

Data Index: 512022 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1124. Min Act: -0.0003

Data Index: 147667 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1132349 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1207. Min Act: -0.0003

Data Index: 43092 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1159. Min Act: -0.0003

Data Index: 631089 (C4 (Web Text))

Max Activating Token Index: 739