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

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

Neuron 154 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4560. Min Act: -0.0000

Data Index: 826797 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1170035 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1106025 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3351. Min Act: -0.0000

Data Index: 140452 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1208319 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2555. Min Act: -0.0000

Data Index: 442084 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2630. Min Act: -0.0000

Data Index: 707341 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2539. Min Act: -0.0000

Data Index: 473263 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2499. Min Act: -0.0000

Data Index: 663529 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1116529 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2347. Min Act: -0.0000

Data Index: 143341 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2432. Min Act: -0.0000

Data Index: 352178 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2493. Min Act: -0.0000

Data Index: 34612 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2801. Min Act: -0.0000

Data Index: 323382 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1308820 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2556. Min Act: -0.0000

Data Index: 567414 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2503. Min Act: -0.0000

Data Index: 955637 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2455. Min Act: -0.0000

Data Index: 746905 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2481. Min Act: -0.0000

Data Index: 343721 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.2424. Min Act: -0.0000

Data Index: 963506 (C4 (Web Text))

Max Activating Token Index: 919