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

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

Neuron 5107 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: 0.4516. Min Range: -0.4516

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1211389 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1077234 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4375. Min Act: -0.0000

Data Index: 566231 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4491. Min Act: -0.0000

Data Index: 590309 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4444. Min Act: -0.0000

Data Index: 705585 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4042. Min Act: -0.0000

Data Index: 59995 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4076. Min Act: -0.0000

Data Index: 933280 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4183. Min Act: -0.0000

Data Index: 577759 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3703. Min Act: -0.0000

Data Index: 682784 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3912. Min Act: -0.0000

Data Index: 316314 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3692. Min Act: -0.0000

Data Index: 277395 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3676. Min Act: -0.0000

Data Index: 560184 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3808. Min Act: -0.0000

Data Index: 933632 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3712. Min Act: -0.0000

Data Index: 615272 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3571. Min Act: -0.0000

Data Index: 564653 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3783. Min Act: -0.0000

Data Index: 862011 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3786. Min Act: -0.0000

Data Index: 906168 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3865. Min Act: -0.0000

Data Index: 992772 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3582. Min Act: -0.0000

Data Index: 364739 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3369. Min Act: -0.0000

Data Index: 699805 (C4 (Web Text))

Max Activating Token Index: 620