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

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

Neuron 4525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6568. Min Range: -3.6568

Max Act: 3.6568. Min Act: -0.0000

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.6568. Min Range: -3.6568

Max Act: 3.2998. Min Act: -0.0000

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1214737 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0471. Min Act: -0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0275. Min Act: -0.0000

Data Index: 45343 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0370. Min Act: -0.0000

Data Index: 1338562 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0369. Min Act: -0.0000

Data Index: 105826 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0371. Min Act: -0.0000

Data Index: 334367 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0341. Min Act: -0.0000

Data Index: 439667 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0343. Min Act: -0.0000

Data Index: 626484 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0367. Min Act: -0.0000

Data Index: 397006 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1351666 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0331. Min Act: -0.0000

Data Index: 156330 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0307. Min Act: -0.0000

Data Index: 479911 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0305. Min Act: -0.0000

Data Index: 801525 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0327. Min Act: -0.0000

Data Index: 420827 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1318006 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0311. Min Act: -0.0000

Data Index: 817774 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0301. Min Act: -0.0000

Data Index: 73394 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 3.6568. Min Range: -3.6568

Max Act: 0.0300. Min Act: -0.0000

Data Index: 487736 (C4 (Web Text))

Max Activating Token Index: 12