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

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

Neuron 2523 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: 0.1497. Min Range: -0.1497

Max Act: 0.1497. Min Act: -0.0001

Data Index: 342973 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1349. Min Act: -0.0001

Data Index: 978802 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1164180 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1304. Min Act: -0.0001

Data Index: 331081 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1165. Min Act: -0.0001

Data Index: 803516 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1246. Min Act: -0.0001

Data Index: 506797 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1228. Min Act: -0.0001

Data Index: 424150 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1174. Min Act: -0.0001

Data Index: 53995 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1291597 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1276. Min Act: -0.0001

Data Index: 370931 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1198956 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1322677 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1029. Min Act: -0.0001

Data Index: 615293 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1171321 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1051646 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1133. Min Act: -0.0001

Data Index: 921970 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1169. Min Act: -0.0001

Data Index: 785654 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1117. Min Act: -0.0001

Data Index: 849132 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1071. Min Act: -0.0001

Data Index: 494523 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.1497. Min Range: -0.1497

Max Act: 0.1208. Min Act: -0.0001

Data Index: 670105 (C4 (Web Text))

Max Activating Token Index: 354