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

Dataset: The Pile

Neuron 3461 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: 1.0383. Min Range: -1.0383

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1988915 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9949. Min Act: -0.0000

Data Index: 756148 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9498. Min Act: -0.0000

Data Index: 178454 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.0383. Min Range: -1.0383

Max Act: 1.0383. Min Act: -0.0000

Data Index: 892199 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9195. Min Act: -0.0000

Data Index: 835055 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8988. Min Act: -0.0000

Data Index: 596158 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1365258 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1627565 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8805. Min Act: -0.0000

Data Index: 860989 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9201. Min Act: -0.0000

Data Index: 99336 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1128152 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8414. Min Act: -0.0000

Data Index: 195719 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1231736 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1591904 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1849095 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1321239 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8743. Min Act: -0.0000

Data Index: 12296 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1806174 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8628. Min Act: -0.0000

Data Index: 24028 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 1.0383. Min Range: -1.0383

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1444855 (The Pile)

Max Activating Token Index: 17