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

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

Neuron 4000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0586. Min Act: -0.0002

Data Index: 820011 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1016142 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0514. Min Act: -0.0002

Data Index: 709434 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0521. Min Act: -0.0002

Data Index: 3276 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0496. Min Act: -0.0002

Data Index: 455699 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0472. Min Act: -0.0002

Data Index: 404475 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0458. Min Act: -0.0002

Data Index: 232568 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1257148 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0519. Min Act: -0.0002

Data Index: 987720 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0460. Min Act: -0.0002

Data Index: 493456 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0438. Min Act: -0.0002

Data Index: 89976 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0473. Min Act: -0.0002

Data Index: 632443 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0461. Min Act: -0.0002

Data Index: 769184 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1140616 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0464. Min Act: -0.0002

Data Index: 244239 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0417. Min Act: -0.0002

Data Index: 71957 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0425. Min Act: -0.0002

Data Index: 477252 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0418. Min Act: -0.0002

Data Index: 432720 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0437. Min Act: -0.0002

Data Index: 936210 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0586. Min Range: -0.0586

Max Act: 0.0438. Min Act: -0.0002

Data Index: 708139 (C4 (Web Text))

Max Activating Token Index: 194