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

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

Neuron 3735 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: 0.0576. Min Range: -0.0576

Max Act: 0.0570. Min Act: -0.0002

Data Index: 215105 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0002

Data Index: 133553 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1234088 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0498. Min Act: -0.0002

Data Index: 94249 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0485. Min Act: -0.0003

Data Index: 740927 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0454. Min Act: -0.0002

Data Index: 240194 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0443. Min Act: -0.0002

Data Index: 266092 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0439. Min Act: -0.0002

Data Index: 40591 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0445. Min Act: -0.0002

Data Index: 421211 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0459. Min Act: -0.0002

Data Index: 829890 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0451. Min Act: -0.0002

Data Index: 290966 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0436. Min Act: -0.0002

Data Index: 172731 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0430. Min Act: -0.0002

Data Index: 361623 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0429. Min Act: -0.0002

Data Index: 521497 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0415. Min Act: -0.0002

Data Index: 442051 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0425. Min Act: -0.0002

Data Index: 427359 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0419. Min Act: -0.0002

Data Index: 146910 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0427. Min Act: -0.0002

Data Index: 168040 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0430. Min Act: -0.0002

Data Index: 812115 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0422. Min Act: -0.0002

Data Index: 330266 (C4 (Web Text))

Max Activating Token Index: 165