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

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

Neuron 1947 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9557. Min Act: -0.0000

Data Index: 176956 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9964. Min Act: 0.0000

Data Index: 487790 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7327. Min Act: -0.0000

Data Index: 896617 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7654. Min Act: -0.0000

Data Index: 12804 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7159. Min Act: 0.0001

Data Index: 151829 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1193611 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1179570 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7816. Min Act: 0.0000

Data Index: 872889 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1186747 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1140960 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1102212 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1318698 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7028. Min Act: -0.0000

Data Index: 996601 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6433. Min Act: -0.0000

Data Index: 133638 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6595. Min Act: 0.0000

Data Index: 505345 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6838. Min Act: 0.0000

Data Index: 508341 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6850. Min Act: -0.0000

Data Index: 390481 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6370. Min Act: -0.0000

Data Index: 22439 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6409. Min Act: -0.0000

Data Index: 29685 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6344. Min Act: 0.0000

Data Index: 309654 (C4 (Web Text))

Max Activating Token Index: 508