Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1156502 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1294900 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1862. Min Act: -0.0001

Data Index: 928934 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1747. Min Act: -0.0001

Data Index: 95584 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1640. Min Act: -0.0001

Data Index: 991170 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1337316 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1520. Min Act: -0.0001

Data Index: 496351 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1495. Min Act: -0.0001

Data Index: 888702 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1586. Min Act: -0.0001

Data Index: 872085 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1465. Min Act: -0.0001

Data Index: 728346 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1377. Min Act: -0.0001

Data Index: 988744 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1458. Min Act: -0.0001

Data Index: 891066 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1445. Min Act: -0.0001

Data Index: 756066 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1448. Min Act: -0.0001

Data Index: 509785 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1526. Min Act: -0.0000

Data Index: 314588 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1179619 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1463. Min Act: -0.0001

Data Index: 329441 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1404. Min Act: -0.0001

Data Index: 54053 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1395. Min Act: -0.0001

Data Index: 290846 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1387. Min Act: -0.0001

Data Index: 55319 (C4 (Web Text))

Max Activating Token Index: 450