Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0837. Min Act: -0.0002

Data Index: 94634 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0653. Min Act: -0.0002

Data Index: 399026 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1253224 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0611. Min Act: -0.0002

Data Index: 321091 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0568. Min Act: -0.0002

Data Index: 254269 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0589. Min Act: -0.0002

Data Index: 637482 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0569. Min Act: -0.0002

Data Index: 949485 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0549. Min Act: -0.0002

Data Index: 826309 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1095119 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0562. Min Act: -0.0002

Data Index: 528292 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0557. Min Act: -0.0002

Data Index: 857888 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0533. Min Act: -0.0002

Data Index: 324252 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0546. Min Act: -0.0002

Data Index: 603305 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1321331 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0552. Min Act: -0.0002

Data Index: 12550 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1001125 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0553. Min Act: -0.0002

Data Index: 551187 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0513. Min Act: -0.0002

Data Index: 558299 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0534. Min Act: -0.0002

Data Index: 500207 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0552. Min Act: -0.0002

Data Index: 7063 (C4 (Web Text))

Max Activating Token Index: 729