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

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

Neuron 428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0662. Min Act: -0.0001

Data Index: 852627 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1347799 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1164437 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0649. Min Act: -0.0001

Data Index: 65671 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1245244 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1055648 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0605. Min Act: -0.0001

Data Index: 916642 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0001

Data Index: 507705 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0587. Min Act: -0.0001

Data Index: 319966 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0537. Min Act: -0.0001

Data Index: 906679 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0580. Min Act: -0.0001

Data Index: 433545 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1114292 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0575. Min Act: -0.0001

Data Index: 193205 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0557. Min Act: -0.0001

Data Index: 936081 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0579. Min Act: -0.0001

Data Index: 977965 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1243581 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0540. Min Act: -0.0001

Data Index: 344085 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0502. Min Act: -0.0001

Data Index: 816979 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0575. Min Act: -0.0001

Data Index: 746886 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1230668 (C4 (Web Text))

Max Activating Token Index: 748