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

Dataset: The Pile

Neuron 3539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0542. Min Range: -1.0542

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1788369 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.0542. Min Range: -1.0542

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1041884 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9336. Min Act: -0.0000

Data Index: 765815 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8975. Min Act: -0.0000

Data Index: 518284 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1400278 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1665625 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1986771 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8794. Min Act: -0.0000

Data Index: 668874 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1774829 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1234548 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1797380 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1241800 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1095173 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1416996 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1412583 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1163827 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7925. Min Act: -0.0000

Data Index: 860632 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7162. Min Act: -0.0000

Data Index: 851973 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1181021 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1497252 (The Pile)

Max Activating Token Index: 48