Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.4165. Min Act: -0.0000

Data Index: 239263 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1213297 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1560. Min Act: -0.0001

Data Index: 132211 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.2099. Min Act: 0.0000

Data Index: 597889 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0124. Min Act: -0.0000

Data Index: 357976 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0072. Min Act: -0.0001

Data Index: 79499 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1782909 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9806. Min Act: -0.0000

Data Index: 571763 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1999881 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9590. Min Act: -0.0001

Data Index: 601395 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9930. Min Act: 0.0000

Data Index: 1651027 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9734. Min Act: -0.0001

Data Index: 1058120 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9721. Min Act: -0.0000

Data Index: 960580 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9291. Min Act: 0.0000

Data Index: 1876156 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9580. Min Act: -0.0001

Data Index: 1526020 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9564. Min Act: 0.0000

Data Index: 757851 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1010036 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0328. Min Act: -0.0001

Data Index: 898680 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9577. Min Act: -0.0001

Data Index: 1135180 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1534695 (The Pile)

Max Activating Token Index: 248