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

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

Neuron 79 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0407. Min Act: -0.0004

Data Index: 438038 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0004

Data Index: 1414622 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1377207 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0381. Min Act: -0.0004

Data Index: 217656 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0390. Min Act: -0.0004

Data Index: 1633019 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1323094 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0348. Min Act: -0.0004

Data Index: 1302196 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1434231 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0349. Min Act: -0.0004

Data Index: 1476281 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0328. Min Act: -0.0004

Data Index: 1447781 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1269052 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0338. Min Act: -0.0004

Data Index: 417007 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1269027 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1384498 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1623469 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1072462 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0320. Min Act: -0.0004

Data Index: 877479 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1545992 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1089893 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0310. Min Act: -0.0004

Data Index: 188179 (C4 (Web Text))

Max Activating Token Index: 236