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

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

Neuron 1478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1446136 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1276833 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2927. Min Act: -0.0000

Data Index: 778596 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1259840 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1357557 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2999. Min Act: -0.0000

Data Index: 471620 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2700. Min Act: -0.0000

Data Index: 839227 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2883. Min Act: -0.0000

Data Index: 381471 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2656. Min Act: -0.0000

Data Index: 482514 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2411. Min Act: -0.0000

Data Index: 782394 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2635. Min Act: -0.0000

Data Index: 78953 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2623. Min Act: -0.0000

Data Index: 625799 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2677. Min Act: -0.0000

Data Index: 678160 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2571. Min Act: -0.0000

Data Index: 875786 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2764. Min Act: -0.0000

Data Index: 827058 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1241448 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2704. Min Act: -0.0000

Data Index: 563519 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1021826 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2502. Min Act: -0.0000

Data Index: 485794 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.2607. Min Act: -0.0000

Data Index: 93786 (C4 (Web Text))

Max Activating Token Index: 845