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

Dataset: The Pile

Neuron 687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0003. Min Range: -1.0003

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1632683 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9588. Min Act: -0.0000

Data Index: 898478 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1611359 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8470. Min Act: -0.0000

Data Index: 379866 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1210420 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7885. Min Act: -0.0000

Data Index: 967604 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1150059 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7913. Min Act: -0.0000

Data Index: 319349 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7459. Min Act: -0.0000

Data Index: 74603 (The Pile)

Max Activating Token Index: 171

Text #9

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7151. Min Act: -0.0000

Data Index: 154338 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7329. Min Act: -0.0000

Data Index: 932795 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1821897 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7225. Min Act: -0.0000

Data Index: 439883 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1699669 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1212246 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1694548 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1208587 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1826996 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1330220 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6726. Min Act: -0.0000

Data Index: 696083 (The Pile)

Max Activating Token Index: 828