Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5728 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.4664. Min Act: -0.0001

Data Index: 50003 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.4434. Min Act: -0.0001

Data Index: 607508 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.4370. Min Act: -0.0001

Data Index: 667791 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3693. Min Act: -0.0001

Data Index: 938659 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3739. Min Act: -0.0001

Data Index: 871580 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3513. Min Act: -0.0001

Data Index: 449884 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3566. Min Act: -0.0000

Data Index: 916361 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3217. Min Act: -0.0001

Data Index: 936876 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3488. Min Act: -0.0001

Data Index: 435106 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3162. Min Act: -0.0001

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.2887. Min Act: -0.0001

Data Index: 38317 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3145. Min Act: -0.0001

Data Index: 684820 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3229. Min Act: -0.0001

Data Index: 1279295 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3189. Min Act: -0.0001

Data Index: 367729 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3320. Min Act: -0.0001

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.2999. Min Act: -0.0001

Data Index: 1019904 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3014. Min Act: -0.0001

Data Index: 14606 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.2873. Min Act: -0.0001

Data Index: 739207 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.2965. Min Act: -0.0001

Data Index: 1155260 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.4664. Min Range: -0.4664

Max Act: 0.3015. Min Act: -0.0001

Data Index: 906610 (C4 (Web Text))

Max Activating Token Index: 455