Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1308 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.8658. Min Act: 0.0000

Data Index: 988977 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7758. Min Act: 0.0000

Data Index: 1132955 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.8105. Min Act: -0.0000

Data Index: 459832 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.7068. Min Act: -0.0000

Data Index: 753681 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6944. Min Act: 0.0000

Data Index: 1189623 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6499. Min Act: -0.0000

Data Index: 295604 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6390. Min Act: -0.0000

Data Index: 470674 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6026. Min Act: -0.0000

Data Index: 505437 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6491. Min Act: 0.0000

Data Index: 1284070 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6079. Min Act: -0.0000

Data Index: 482775 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1334148 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5974. Min Act: 0.0000

Data Index: 242747 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1218365 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1136970 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5265. Min Act: -0.0000

Data Index: 180905 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1241159 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5524. Min Act: -0.0000

Data Index: 69060 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5421. Min Act: -0.0000

Data Index: 652252 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5118. Min Act: -0.0000

Data Index: 328804 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.8658. Min Range: -0.8658

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1180844 (C4 (Web Text))

Max Activating Token Index: 837