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

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

Neuron 2157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.7892. Min Act: -0.0000

Data Index: 468308 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.7087. Min Act: -0.0000

Data Index: 520663 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.6330. Min Act: -0.0000

Data Index: 431893 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.5085. Min Act: -0.0000

Data Index: 861304 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3849. Min Act: -0.0000

Data Index: 362417 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.4808. Min Act: -0.0000

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3965. Min Act: -0.0000

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.5208. Min Act: -0.0000

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3791. Min Act: -0.0000

Data Index: 584909 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3340. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3258. Min Act: -0.0000

Data Index: 1043769 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3304. Min Act: -0.0000

Data Index: 90301 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.4422. Min Act: -0.0000

Data Index: 36967 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.4055. Min Act: -0.0000

Data Index: 890772 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.1487. Min Act: -0.0000

Data Index: 290275 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.3950. Min Act: -0.0000

Data Index: 313080 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.1519. Min Act: -0.0000

Data Index: 32697 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.2501. Min Act: -0.0000

Data Index: 1278820 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.7892. Min Range: -2.7892

Max Act: 2.2567. Min Act: -0.0000

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 988