Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1355478 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.2642. Min Act: -0.0000

Data Index: 395841 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.3275. Min Act: -0.0000

Data Index: 799202 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.3646. Min Act: -0.0000

Data Index: 774489 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.2670. Min Act: -0.0000

Data Index: 665976 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1267138 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.1347. Min Act: -0.0000

Data Index: 780375 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1049726 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.1094. Min Act: -0.0000

Data Index: 694588 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.1031. Min Act: -0.0000

Data Index: 501354 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0677. Min Act: -0.0000

Data Index: 825678 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1068616 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1030377 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0278. Min Act: -0.0000

Data Index: 368150 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1252360 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0425. Min Act: -0.0000

Data Index: 557474 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0369. Min Act: -0.0000

Data Index: 397083 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.5051. Min Range: -1.5051

Max Act: 0.9767. Min Act: -0.0000

Data Index: 191501 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0284. Min Act: -0.0000

Data Index: 3364 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 1.5051. Min Range: -1.5051

Max Act: 1.0381. Min Act: -0.0000

Data Index: 462397 (C4 (Web Text))

Max Activating Token Index: 197