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

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

Neuron 4544 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: 3.3038. Min Range: -3.3038

Max Act: 3.3038. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9777. Min Act: -0.0000

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9687. Min Act: -0.0000

Data Index: 85834 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.7292. Min Act: -0.0000

Data Index: 409901 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.7216. Min Act: -0.0000

Data Index: 1153245 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.9634. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.7694. Min Act: -0.0000

Data Index: 1224024 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.8546. Min Act: -0.0000

Data Index: 1061716 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.7205. Min Act: -0.0000

Data Index: 552264 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.7182. Min Act: -0.0000

Data Index: 221248 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1030878 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.6608. Min Act: -0.0000

Data Index: 1212409 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.6251. Min Act: -0.0000

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.4351. Min Act: -0.0000

Data Index: 291714 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.5657. Min Act: -0.0000

Data Index: 1352480 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.5574. Min Act: -0.0000

Data Index: 437893 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.5530. Min Act: -0.0000

Data Index: 1140395 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.5282. Min Act: -0.0000

Data Index: 329163 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.6788. Min Act: -0.0000

Data Index: 34527 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 3.3038. Min Range: -3.3038

Max Act: 2.4841. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 474