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

Dataset: The Pile

Neuron 2038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.5340. Min Act: -0.0000

Data Index: 891195 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.5403. Min Act: -0.0000

Data Index: 233732 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4270. Min Act: -0.0000

Data Index: 158434 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3813. Min Act: -0.0000

Data Index: 584776 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4730. Min Act: -0.0000

Data Index: 556198 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4842. Min Act: -0.0000

Data Index: 541650 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1455684 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1320263 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1919584 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1992. Min Act: -0.0000

Data Index: 127849 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1425453 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1103445 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2251. Min Act: -0.0000

Data Index: 586931 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1964190 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1133841 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.1382. Min Act: -0.0000

Data Index: 978864 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0947. Min Act: -0.0000

Data Index: 884947 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1487695 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.2010. Min Act: -0.0000

Data Index: 149229 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 1.5403. Min Range: -1.5403

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1054048 (The Pile)

Max Activating Token Index: 160