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

Dataset: The Pile

Neuron 3424 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: 0.9616. Min Range: -0.9616

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1157345 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1279702 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1287430 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7349. Min Act: -0.0000

Data Index: 984847 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7240. Min Act: -0.0000

Data Index: 525039 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7212. Min Act: -0.0000

Data Index: 278226 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7140. Min Act: -0.0000

Data Index: 125119 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.7089. Min Act: -0.0000

Data Index: 544102 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1318081 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1390016 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6665. Min Act: -0.0000

Data Index: 48193 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1537182 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6106. Min Act: -0.0000

Data Index: 367240 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6656. Min Act: -0.0000

Data Index: 434320 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6442. Min Act: -0.0000

Data Index: 271448 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6355. Min Act: -0.0000

Data Index: 266637 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6393. Min Act: -0.0000

Data Index: 298200 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.5922. Min Act: -0.0000

Data Index: 757859 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6130. Min Act: -0.0000

Data Index: 797550 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.9616. Min Range: -0.9616

Max Act: 0.6309. Min Act: -0.0000

Data Index: 539733 (The Pile)

Max Activating Token Index: 627