Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0837. Min Act: -0.0005

Data Index: 1149041 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0628. Min Act: -0.0005

Data Index: 254097 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0652. Min Act: -0.0005

Data Index: 784240 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0617. Min Act: -0.0005

Data Index: 896978 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0573. Min Act: -0.0005

Data Index: 976306 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0586. Min Act: -0.0005

Data Index: 336323 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0585. Min Act: -0.0005

Data Index: 13612 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0582. Min Act: -0.0005

Data Index: 743964 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0598. Min Act: -0.0005

Data Index: 1263561 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0590. Min Act: -0.0005

Data Index: 116495 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0531. Min Act: -0.0005

Data Index: 113115 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0541. Min Act: -0.0005

Data Index: 837154 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0578. Min Act: -0.0005

Data Index: 589966 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0536. Min Act: -0.0005

Data Index: 995385 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0552. Min Act: -0.0005

Data Index: 30407 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0510. Min Act: -0.0005

Data Index: 486312 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0475. Min Act: -0.0005

Data Index: 987348 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0566. Min Act: -0.0005

Data Index: 365907 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0536. Min Act: -0.0005

Data Index: 594107 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0519. Min Act: -0.0005

Data Index: 887599 (C4 (Web Text))

Max Activating Token Index: 88