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

Dataset: The Pile

Neuron 1549 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: 1.6171. Min Range: -1.6171

Max Act: 1.5937. Min Act: -0.0000

Data Index: 51135 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.5300. Min Act: 0.0000

Data Index: 1929348 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.6171. Min Act: -0.0000

Data Index: 1167098 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1935. Min Act: -0.0000

Data Index: 318752 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1587415 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1982042 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1830. Min Act: -0.0000

Data Index: 52583 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3448. Min Act: -0.0000

Data Index: 172806 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2444. Min Act: -0.0000

Data Index: 196159 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1337243 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1832. Min Act: -0.0000

Data Index: 935388 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1591. Min Act: -0.0000

Data Index: 258859 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1479313 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1201282 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1328260 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1727. Min Act: -0.0000

Data Index: 900641 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.0953. Min Act: -0.0000

Data Index: 85100 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1531938 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1169628 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.0751. Min Act: -0.0000

Data Index: 79171 (The Pile)

Max Activating Token Index: 614