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

Dataset: The Pile

Neuron 4081 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: 1.3120. Min Range: -1.3120

Max Act: 1.3120. Min Act: -0.0000

Data Index: 255946 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1380. Min Act: -0.0000

Data Index: 801060 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1818413 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1069. Min Act: -0.0000

Data Index: 777532 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1194450 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9880. Min Act: -0.0000

Data Index: 549384 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1112806 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1212567 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0110. Min Act: -0.0000

Data Index: 671113 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9816. Min Act: -0.0000

Data Index: 342692 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1157504 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9731. Min Act: -0.0000

Data Index: 796954 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1254044 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1521231 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1136914 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1616159 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1870042 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1469700 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1796296 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1471158 (The Pile)

Max Activating Token Index: 486