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

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

Neuron 2772 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.5458. Min Act: -0.0000

Data Index: 1311013 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.5329. Min Act: -0.0000

Data Index: 499292 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.5389. Min Act: -0.0000

Data Index: 268865 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.2661. Min Act: -0.0000

Data Index: 81045 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.3951. Min Act: -0.0000

Data Index: 92091 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.1201. Min Act: -0.0000

Data Index: 336138 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.3053. Min Act: -0.0000

Data Index: 52611 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.3841. Min Act: -0.0000

Data Index: 128912 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.2580. Min Act: -0.0000

Data Index: 18647 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.0089. Min Act: -0.0000

Data Index: 287669 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.1921. Min Act: -0.0000

Data Index: 245703 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.2090. Min Act: -0.0000

Data Index: 498105 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.3475. Min Act: -0.0000

Data Index: 345889 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.2018. Min Act: -0.0000

Data Index: 1078276 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.0627. Min Act: -0.0000

Data Index: 694793 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.3984. Min Act: -0.0000

Data Index: 986929 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.0480. Min Act: -0.0001

Data Index: 1140968 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 2.5458. Min Range: -2.5458

Max Act: 1.9986. Min Act: -0.0000

Data Index: 106830 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.0097. Min Act: -0.0000

Data Index: 86784 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 2.5458. Min Range: -2.5458

Max Act: 2.2235. Min Act: -0.0000

Data Index: 740065 (C4 (Web Text))

Max Activating Token Index: 178