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

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

Neuron 2750 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: 1.1044. Min Range: -1.1044

Max Act: 1.1044. Min Act: -0.0003

Data Index: 537911 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8858. Min Act: -0.0003

Data Index: 603737 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9192. Min Act: -0.0003

Data Index: 792087 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8684. Min Act: -0.0003

Data Index: 125837 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8450. Min Act: -0.0003

Data Index: 815636 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8121. Min Act: -0.0003

Data Index: 883811 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8131. Min Act: -0.0003

Data Index: 469003 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8010. Min Act: -0.0003

Data Index: 478128 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7718. Min Act: -0.0003

Data Index: 1062431 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7440. Min Act: -0.0003

Data Index: 699377 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7437. Min Act: -0.0003

Data Index: 897945 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7689. Min Act: -0.0003

Data Index: 308336 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8329. Min Act: -0.0003

Data Index: 1340302 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7079. Min Act: -0.0003

Data Index: 1199431 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7510. Min Act: -0.0003

Data Index: 847288 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7312. Min Act: -0.0003

Data Index: 233740 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7465. Min Act: -0.0003

Data Index: 1046157 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7366. Min Act: -0.0003

Data Index: 511475 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7514. Min Act: -0.0003

Data Index: 435943 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7609. Min Act: -0.0003

Data Index: 592252 (C4 (Web Text))

Max Activating Token Index: 520