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

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

Neuron 1139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.2050. Min Act: -0.0000

Data Index: 723431 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1506. Min Act: -0.0000

Data Index: 488655 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1268230 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1428. Min Act: -0.0001

Data Index: 854732 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1471. Min Act: -0.0000

Data Index: 55974 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1361. Min Act: -0.0000

Data Index: 247603 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1146079 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1369. Min Act: -0.0000

Data Index: 883122 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1336. Min Act: -0.0001

Data Index: 610745 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1162584 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1098497 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1260. Min Act: -0.0000

Data Index: 858537 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1205. Min Act: -0.0001

Data Index: 344660 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1291. Min Act: -0.0001

Data Index: 53112 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1189. Min Act: -0.0000

Data Index: 214464 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1265. Min Act: -0.0000

Data Index: 109654 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1132. Min Act: -0.0000

Data Index: 567941 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1257. Min Act: -0.0000

Data Index: 808133 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1205. Min Act: -0.0000

Data Index: 903153 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.2050. Min Range: -0.2050

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1184233 (C4 (Web Text))

Max Activating Token Index: 215