Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2760. Min Act: -0.0000

Data Index: 597316 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1151485 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1218718 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6822. Min Act: -0.0000

Data Index: 258404 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1169117 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6306. Min Act: -0.0000

Data Index: 165726 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6491. Min Act: -0.0001

Data Index: 761706 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1312824 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6451. Min Act: -0.0001

Data Index: 261757 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1319293 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6381. Min Act: -0.0000

Data Index: 720814 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6385. Min Act: -0.0000

Data Index: 485530 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6096. Min Act: -0.0000

Data Index: 728376 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.6243. Min Act: -0.0000

Data Index: 41680 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1189420 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1584496 (Python Code)

Max Activating Token Index: 860

Text #16

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5844. Min Act: -0.0001

Data Index: 205039 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5642. Min Act: -0.0000

Data Index: 951478 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1384460 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 1.2760. Min Range: -1.2760

Max Act: 0.5520. Min Act: -0.0000

Data Index: 882891 (C4 (Web Text))

Max Activating Token Index: 172