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

Dataset: The Pile

Neuron 3639 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: 0.7127. Min Range: -0.7127

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1817842 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1078910 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6645. Min Act: -0.0000

Data Index: 525421 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1527497 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6329. Min Act: -0.0000

Data Index: 157949 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6178. Min Act: -0.0000

Data Index: 985222 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1202744 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5795. Min Act: -0.0000

Data Index: 620109 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1480634 (The Pile)

Max Activating Token Index: 602

Text #9

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1946135 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6100. Min Act: -0.0000

Data Index: 961789 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1673365 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5543. Min Act: -0.0000

Data Index: 347125 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1423543 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1329727 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1190646 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1887891 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1998524 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.6017. Min Act: -0.0000

Data Index: 745028 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.7127. Min Range: -0.7127

Max Act: 0.5831. Min Act: -0.0000

Data Index: 483987 (The Pile)

Max Activating Token Index: 255