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

Dataset: The Pile

Neuron 830 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: 1.3842. Min Range: -1.3842

Max Act: 1.3315. Min Act: -0.0000

Data Index: 615024 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1170630 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1494276 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2254. Min Act: -0.0000

Data Index: 724680 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2538. Min Act: -0.0001

Data Index: 1209405 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1424200 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2304. Min Act: -0.0000

Data Index: 659746 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1087870 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1526428 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1841. Min Act: -0.0000

Data Index: 529604 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1676504 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1780. Min Act: -0.0000

Data Index: 66081 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2038. Min Act: -0.0000

Data Index: 567822 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1806438 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1145. Min Act: -0.0000

Data Index: 71026 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1013. Min Act: -0.0000

Data Index: 193154 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1818779 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1389122 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1837. Min Act: -0.0000

Data Index: 924517 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2186. Min Act: -0.0000

Data Index: 798377 (The Pile)

Max Activating Token Index: 764