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

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

Neuron 1538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0003

Data Index: 571517 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0370. Min Act: -0.0003

Data Index: 99198 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0330. Min Act: -0.0003

Data Index: 55175 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1092346 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0339. Min Act: -0.0003

Data Index: 962773 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1188065 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0321. Min Act: -0.0003

Data Index: 423409 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0304. Min Act: -0.0003

Data Index: 465702 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0345. Min Act: -0.0003

Data Index: 520439 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1143467 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0293. Min Act: -0.0003

Data Index: 163598 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1153092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0277. Min Act: -0.0003

Data Index: 746341 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0254. Min Act: -0.0003

Data Index: 480573 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0276. Min Act: -0.0003

Data Index: 228914 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1368563 (Python Code)

Max Activating Token Index: 530

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0293. Min Act: -0.0003

Data Index: 319243 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1399424 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1334904 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0288. Min Act: -0.0003

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 246