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

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

Neuron 4650 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0000

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1426987 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1337346 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0293. Min Act: -0.0000

Data Index: 296620 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0344. Min Act: -0.0000

Data Index: 515836 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0281. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0279. Min Act: -0.0000

Data Index: 151341 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1573621 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0028. Min Act: -0.0000

Data Index: 1373689 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0261. Min Act: -0.0000

Data Index: 936492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0078. Min Act: -0.0000

Data Index: 325516 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0279. Min Act: -0.0000

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1599665 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0262. Min Act: -0.0000

Data Index: 587814 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0273. Min Act: -0.0000

Data Index: 931058 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1294127 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1029216 (C4 (Web Text))

Max Activating Token Index: 1023