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

Dataset: The Pile

Neuron 3781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0171. Min Range: -1.0171

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1213459 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1546385 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.9190. Min Act: -0.0000

Data Index: 953245 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1729076 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1111249 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.9341. Min Act: -0.0000

Data Index: 59979 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1338506 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.8164. Min Act: -0.0000

Data Index: 659046 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7716. Min Act: -0.0000

Data Index: 6388 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.8235. Min Act: -0.0000

Data Index: 929274 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7890. Min Act: -0.0000

Data Index: 579106 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7924. Min Act: -0.0000

Data Index: 727032 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7661. Min Act: -0.0000

Data Index: 161251 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1718771 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7751. Min Act: -0.0000

Data Index: 812186 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1788040 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1878703 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.7827. Min Act: -0.0000

Data Index: 413404 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.6872. Min Act: -0.0000

Data Index: 669753 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 1.0171. Min Range: -1.0171

Max Act: 0.8055. Min Act: -0.0000

Data Index: 201170 (The Pile)

Max Activating Token Index: 567