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

Dataset: The Pile

Neuron 1043 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: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1832740 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4703. Min Act: -0.0000

Data Index: 318684 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4645. Min Act: -0.0000

Data Index: 213946 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4291. Min Act: -0.0000

Data Index: 30122 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1965311 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4285. Min Act: -0.0000

Data Index: 268333 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1407584 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4822. Min Act: -0.0000

Data Index: 406405 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1717442 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4331. Min Act: -0.0001

Data Index: 408351 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4266. Min Act: -0.0000

Data Index: 2451 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4248. Min Act: -0.0000

Data Index: 489752 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1665324 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1861352 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1708963 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3899. Min Act: -0.0000

Data Index: 448441 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4761. Min Act: -0.0000

Data Index: 113207 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1024191 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4651. Min Act: -0.0000

Data Index: 695004 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1766928 (The Pile)

Max Activating Token Index: 110