Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0698. Min Act: -0.0003

Data Index: 911659 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1251223 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0646. Min Act: -0.0003

Data Index: 708490 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0612. Min Act: -0.0003

Data Index: 906758 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1320789 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1325200 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1209264 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0577. Min Act: -0.0003

Data Index: 785533 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0578. Min Act: -0.0003

Data Index: 699470 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1304723 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0612. Min Act: -0.0003

Data Index: 967499 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0564. Min Act: -0.0003

Data Index: 161125 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0609. Min Act: -0.0003

Data Index: 279260 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0587. Min Act: -0.0003

Data Index: 8471 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0564. Min Act: -0.0003

Data Index: 937303 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1268205 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1300333 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0585. Min Act: -0.0003

Data Index: 981844 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0574. Min Act: -0.0003

Data Index: 957866 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0590. Min Act: -0.0003

Data Index: 51941 (C4 (Web Text))

Max Activating Token Index: 813