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

Dataset: The Pile

Neuron 2675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.7142. Min Act: -0.0000

Data Index: 467022 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4865. Min Act: -0.0000

Data Index: 235808 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4984. Min Act: -0.0000

Data Index: 495052 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.3897. Min Act: -0.0000

Data Index: 117114 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4094. Min Act: -0.0000

Data Index: 907306 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.1368. Min Act: -0.0000

Data Index: 1030820 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5464. Min Act: -0.0000

Data Index: 730779 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.3272. Min Act: -0.0000

Data Index: 646225 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.1115. Min Act: -0.0000

Data Index: 1205909 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.0825. Min Act: -0.0000

Data Index: 791762 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.0478. Min Act: -0.0000

Data Index: 1312374 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.1859. Min Act: -0.0000

Data Index: 246318 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.2030. Min Act: -0.0000

Data Index: 1722113 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.2924. Min Act: -0.0000

Data Index: 795890 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.0927. Min Act: -0.0000

Data Index: 1841171 (The Pile)

Max Activating Token Index: 196

Text #15

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.0245. Min Act: -0.0000

Data Index: 347411 (The Pile)

Max Activating Token Index: 210

Text #16

Max Range: 3.7142. Min Range: -3.7142

Max Act: 2.9916. Min Act: -0.0000

Data Index: 1681035 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 3.7142. Min Range: -3.7142

Max Act: 2.7021. Min Act: -0.0000

Data Index: 8326 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 3.7142. Min Range: -3.7142

Max Act: 2.9637. Min Act: -0.0000

Data Index: 22754 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 3.7142. Min Range: -3.7142

Max Act: 2.9050. Min Act: -0.0000

Data Index: 1133342 (The Pile)

Max Activating Token Index: 94