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

Dataset: The Pile

Neuron 2386 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.9893. Min Act: -0.0000

Data Index: 1307402 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.8615. Min Act: -0.0000

Data Index: 118187 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.6108. Min Act: -0.0000

Data Index: 1950148 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.1658. Min Act: -0.0000

Data Index: 446339 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.1807. Min Act: -0.0000

Data Index: 1256245 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.8129. Min Act: -0.0000

Data Index: 1240783 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.0781. Min Act: -0.0000

Data Index: 975111 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.4749. Min Act: -0.0000

Data Index: 33952 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.4724. Min Act: -0.0000

Data Index: 812511 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.9885. Min Act: -0.0000

Data Index: 33005 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.7622. Min Act: -0.0000

Data Index: 443995 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.9071. Min Act: -0.0000

Data Index: 336345 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.5566. Min Act: -0.0000

Data Index: 763203 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.9857. Min Act: -0.0000

Data Index: 1446786 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.2834. Min Act: -0.0000

Data Index: 435235 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.5852. Min Act: -0.0000

Data Index: 1138218 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 7.9893. Min Range: -7.9893

Max Act: 7.0338. Min Act: -0.0000

Data Index: 1282646 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.7638. Min Act: -0.0000

Data Index: 1111680 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 7.9893. Min Range: -7.9893

Max Act: 6.8152. Min Act: -0.0000

Data Index: 1353407 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 7.9893. Min Range: -7.9893

Max Act: 5.4856. Min Act: -0.0000

Data Index: 737186 (The Pile)

Max Activating Token Index: 920