Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.9345. Min Act: -0.0000

Data Index: 724030 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.7231. Min Act: -0.0000

Data Index: 510305 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1738698 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1293964 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1695259 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4524. Min Act: -0.0000

Data Index: 471022 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1844922 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1049856 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4172. Min Act: -0.0000

Data Index: 600223 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4481. Min Act: -0.0000

Data Index: 426658 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1471330 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1945190 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1417331 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3471. Min Act: -0.0001

Data Index: 911621 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4358. Min Act: -0.0000

Data Index: 260545 (The Pile)

Max Activating Token Index: 85

Text #15

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3943. Min Act: -0.0000

Data Index: 850576 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3444. Min Act: -0.0000

Data Index: 241871 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1528840 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1342987 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.9345. Min Range: -0.9345

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1256080 (The Pile)

Max Activating Token Index: 318