Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1181853 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.4085. Min Act: -0.0001

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1248665 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3679. Min Act: -0.0000

Data Index: 327011 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3529. Min Act: -0.0000

Data Index: 824294 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3338. Min Act: -0.0000

Data Index: 578771 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3321. Min Act: -0.0000

Data Index: 261561 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3073. Min Act: -0.0001

Data Index: 652754 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1050088 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1350002 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2946. Min Act: -0.0000

Data Index: 298367 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1006679 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2795. Min Act: -0.0000

Data Index: 9270 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2777. Min Act: -0.0001

Data Index: 464490 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2701. Min Act: -0.0000

Data Index: 574614 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1053946 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1331268 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1339316 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2700. Min Act: -0.0001

Data Index: 177812 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.4731. Min Range: -0.4731

Max Act: 0.2652. Min Act: -0.0001

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 846