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

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

Neuron 2905 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: 3.3084. Min Range: -3.3084

Max Act: 3.3084. Min Act: -0.0000

Data Index: 1437864 (Python Code)

Max Activating Token Index: 467

Text #1

Max Range: 3.3084. Min Range: -3.3084

Max Act: 2.4457. Min Act: -0.0000

Data Index: 1509412 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.6315. Min Act: -0.0000

Data Index: 1527336 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.7255. Min Act: -0.0000

Data Index: 1624906 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1529182 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1527291 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1579342 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1445384 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1619717 (Python Code)

Max Activating Token Index: 778

Text #9

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.4572. Min Act: -0.0000

Data Index: 1589940 (Python Code)

Max Activating Token Index: 697

Text #10

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1615181 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.4897. Min Act: -0.0000

Data Index: 1640774 (Python Code)

Max Activating Token Index: 192

Text #12

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1580691 (Python Code)

Max Activating Token Index: 393

Text #13

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1624684 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1585052 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1446283 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1625065 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1601607 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1586702 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 3.3084. Min Range: -3.3084

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1541906 (Python Code)

Max Activating Token Index: 872