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

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

Neuron 835 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3510. Min Range: -1.3510

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1528648 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 1.3510. Min Range: -1.3510

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1505060 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 1.3510. Min Range: -1.3510

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1648484 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7464. Min Act: -0.0000

Data Index: 630828 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1411530 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1513749 (Python Code)

Max Activating Token Index: 878

Text #6

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1241720 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1447728 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6798. Min Act: -0.0000

Data Index: 685697 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1653553 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1422332 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6310. Min Act: -0.0000

Data Index: 978998 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6484. Min Act: -0.0000

Data Index: 47076 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6197. Min Act: -0.0000

Data Index: 280682 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1115457 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6041. Min Act: -0.0000

Data Index: 643057 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1485335 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6242. Min Act: -0.0000

Data Index: 566930 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6182. Min Act: -0.0000

Data Index: 838136 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.3510. Min Range: -1.3510

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1119911 (C4 (Web Text))

Max Activating Token Index: 79