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

Dataset: The Pile

Neuron 1835 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.5396. Min Act: -0.0000

Data Index: 263640 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4953. Min Act: -0.0000

Data Index: 774360 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1086143 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1526736 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1025742 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4273. Min Act: -0.0000

Data Index: 482741 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1224040 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4863. Min Act: -0.0000

Data Index: 913718 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4425. Min Act: -0.0000

Data Index: 797067 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4420. Min Act: -0.0000

Data Index: 964159 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1047715 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4246. Min Act: -0.0000

Data Index: 556619 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1345603 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4620. Min Act: -0.0000

Data Index: 482428 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4358. Min Act: -0.0000

Data Index: 938035 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4138. Min Act: -0.0000

Data Index: 516167 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1165183 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1674253 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3933. Min Act: -0.0000

Data Index: 470000 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4362. Min Act: -0.0000

Data Index: 141395 (The Pile)

Max Activating Token Index: 791