Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1447 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0500. Min Act: -0.0003

Data Index: 358574 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1357863 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0450. Min Act: -0.0003

Data Index: 960677 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0493. Min Act: -0.0003

Data Index: 569376 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1263808 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0454. Min Act: -0.0003

Data Index: 903594 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0003

Data Index: 671548 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1202364 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0431. Min Act: -0.0003

Data Index: 135000 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0420. Min Act: -0.0003

Data Index: 472333 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0425. Min Act: -0.0003

Data Index: 819031 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0425. Min Act: -0.0003

Data Index: 510661 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0398. Min Act: -0.0003

Data Index: 619756 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0422. Min Act: -0.0003

Data Index: 786158 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0463. Min Act: -0.0003

Data Index: 383859 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0360. Min Act: -0.0003

Data Index: 978840 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1257074 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0391. Min Act: -0.0003

Data Index: 561339 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0361. Min Act: -0.0003

Data Index: 541354 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0365. Min Act: -0.0003

Data Index: 203001 (C4 (Web Text))

Max Activating Token Index: 826