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

Dataset: The Pile

Neuron 4800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.7476. Min Act: -0.0000

Data Index: 720193 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5607. Min Act: -0.0000

Data Index: 283982 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.6292. Min Act: -0.0000

Data Index: 678071 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.9465. Min Act: -0.0000

Data Index: 1585881 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3703. Min Act: -0.0000

Data Index: 50598 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1396716 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3855. Min Act: -0.0000

Data Index: 605885 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3538. Min Act: -0.0000

Data Index: 419130 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1071395 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1987140 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1354802 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1866212 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4008. Min Act: -0.0000

Data Index: 967823 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.2277. Min Act: -0.0000

Data Index: 227654 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3127. Min Act: -0.0000

Data Index: 197280 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.2727. Min Act: -0.0000

Data Index: 603538 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3669. Min Act: -0.0000

Data Index: 465087 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1677761 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.2848. Min Act: -0.0000

Data Index: 165335 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.2294. Min Act: -0.0000

Data Index: 539376 (The Pile)

Max Activating Token Index: 131