Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0001

Data Index: 412571 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1584. Min Act: -0.0001

Data Index: 21670 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1349. Min Act: -0.0001

Data Index: 792353 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1429. Min Act: -0.0002

Data Index: 547163 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1352. Min Act: -0.0002

Data Index: 114948 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1239. Min Act: -0.0001

Data Index: 471051 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1269. Min Act: -0.0001

Data Index: 19311 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1332878 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1268. Min Act: -0.0001

Data Index: 42011 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1302. Min Act: -0.0001

Data Index: 194388 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1230352 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1258. Min Act: -0.0002

Data Index: 876993 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1216. Min Act: -0.0001

Data Index: 903595 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1070. Min Act: -0.0001

Data Index: 500719 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1091. Min Act: -0.0001

Data Index: 984379 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1342192 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1205. Min Act: -0.0001

Data Index: 841760 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1093. Min Act: -0.0001

Data Index: 708832 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1129. Min Act: -0.0001

Data Index: 950547 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1167. Min Act: -0.0001

Data Index: 961965 (C4 (Web Text))

Max Activating Token Index: 580