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

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

Neuron 948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1016302 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0000

Data Index: 608204 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1054892 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1117237 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1304785 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1288. Min Act: -0.0001

Data Index: 65600 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1158049 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1324. Min Act: -0.0000

Data Index: 542053 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1216. Min Act: -0.0001

Data Index: 436954 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1293. Min Act: -0.0000

Data Index: 480820 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1178185 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1115157 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1192. Min Act: -0.0001

Data Index: 922969 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1145298 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1311447 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1250740 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1088. Min Act: -0.0001

Data Index: 590638 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1178. Min Act: -0.0001

Data Index: 726515 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1133621 (C4 (Web Text))

Max Activating Token Index: 248