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

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

Neuron 272 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: 0.1479. Min Range: -0.1479

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1170344 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1067611 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1397. Min Act: -0.0001

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1292. Min Act: -0.0001

Data Index: 882580 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1338. Min Act: -0.0000

Data Index: 355749 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1262. Min Act: 0.0000

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1191. Min Act: -0.0001

Data Index: 406005 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1097560 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1207608 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1113. Min Act: -0.0001

Data Index: 446625 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1069. Min Act: -0.0001

Data Index: 827615 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1144. Min Act: -0.0001

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1112. Min Act: -0.0001

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1220. Min Act: -0.0001

Data Index: 300823 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1152. Min Act: -0.0000

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1135. Min Act: 0.0000

Data Index: 788454 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1093. Min Act: -0.0001

Data Index: 114232 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1090. Min Act: 0.0000

Data Index: 110471 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1101. Min Act: -0.0000

Data Index: 363468 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1136. Min Act: -0.0000

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 253