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

Dataset: The Pile

Neuron 886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1934862 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 1.0244. Min Range: -1.0244

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1868848 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1587815 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7991. Min Act: -0.0000

Data Index: 977652 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.8746. Min Act: -0.0000

Data Index: 633654 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7982. Min Act: -0.0000

Data Index: 490320 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1199885 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7824. Min Act: -0.0000

Data Index: 17882 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1641057 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7194. Min Act: 0.0000

Data Index: 151771 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7659. Min Act: -0.0000

Data Index: 755414 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7388. Min Act: -0.0000

Data Index: 66225 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1326322 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1317861 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1499547 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7468. Min Act: -0.0000

Data Index: 1700185 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1859931 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1813933 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1073671 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 1.0244. Min Range: -1.0244

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1225176 (The Pile)

Max Activating Token Index: 199