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

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

Neuron 695 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.4321. Min Act: -0.0002

Data Index: 34151 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.4023. Min Act: -0.0002

Data Index: 1270133 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.4298. Min Act: -0.0002

Data Index: 533723 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.3428. Min Act: -0.0002

Data Index: 282535 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2841. Min Act: -0.0002

Data Index: 185114 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2948. Min Act: -0.0002

Data Index: 1439951 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2870. Min Act: -0.0002

Data Index: 697112 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2866. Min Act: -0.0002

Data Index: 843932 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2667. Min Act: -0.0002

Data Index: 532297 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2549. Min Act: -0.0002

Data Index: 205348 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2506. Min Act: -0.0002

Data Index: 347896 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2622. Min Act: -0.0002

Data Index: 1263596 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2309. Min Act: -0.0002

Data Index: 156116 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2470. Min Act: -0.0002

Data Index: 598726 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2708. Min Act: -0.0002

Data Index: 384495 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2403. Min Act: -0.0002

Data Index: 637305 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2771. Min Act: -0.0002

Data Index: 1494332 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2399. Min Act: -0.0002

Data Index: 111076 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2391. Min Act: -0.0002

Data Index: 1466298 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.4321. Min Range: -0.4321

Max Act: 0.2635. Min Act: -0.0002

Data Index: 1589663 (Python Code)

Max Activating Token Index: 630