Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 288 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0521. Min Act: -0.0006

Data Index: 1043004 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0531. Min Act: -0.0006

Data Index: 1272354 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0006

Data Index: 279113 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1346792 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0509. Min Act: -0.0006

Data Index: 1011189 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0516. Min Act: -0.0005

Data Index: 800373 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1080268 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0533. Min Act: -0.0006

Data Index: 78548 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0489. Min Act: -0.0005

Data Index: 838007 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0511. Min Act: -0.0005

Data Index: 137871 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0467. Min Act: -0.0006

Data Index: 114441 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0492. Min Act: -0.0005

Data Index: 754510 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0486. Min Act: -0.0006

Data Index: 474586 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0474. Min Act: -0.0006

Data Index: 898712 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0475. Min Act: -0.0006

Data Index: 278853 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0475. Min Act: -0.0005

Data Index: 484445 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0456. Min Act: -0.0005

Data Index: 227470 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0445. Min Act: -0.0006

Data Index: 362823 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0475. Min Act: -0.0005

Data Index: 493248 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0458. Min Act: -0.0006

Data Index: 27716 (C4 (Web Text))

Max Activating Token Index: 550