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

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

Neuron 1712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.3774. Min Act: -0.0000

Data Index: 600565 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9771. Min Act: -0.0000

Data Index: 167413 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.4721. Min Act: -0.0000

Data Index: 23590 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8967. Min Act: -0.0000

Data Index: 884088 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8985. Min Act: -0.0000

Data Index: 166882 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9539. Min Act: -0.0000

Data Index: 20140 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9201. Min Act: -0.0000

Data Index: 570766 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.4807. Min Act: -0.0000

Data Index: 509884 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5798. Min Act: -0.0000

Data Index: 1026327 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.3015. Min Act: -0.0000

Data Index: 939835 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5382. Min Act: -0.0000

Data Index: 861061 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.7845. Min Act: -0.0000

Data Index: 583954 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.6273. Min Act: -0.0000

Data Index: 153198 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.7562. Min Act: -0.0000

Data Index: 117409 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5892. Min Act: -0.0000

Data Index: 374340 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5777. Min Act: -0.0000

Data Index: 792819 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.4137. Min Act: -0.0000

Data Index: 690664 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5523. Min Act: -0.0000

Data Index: 521059 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5406. Min Act: -0.0000

Data Index: 927038 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1241831 (C4 (Web Text))

Max Activating Token Index: 357