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

Dataset: The Pile

Neuron 365 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: 0.0717. Min Range: -0.0717

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1902238 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1387301 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1140831 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0659. Min Act: -0.0000

Data Index: 984720 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0630. Min Act: -0.0000

Data Index: 1009988 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0657. Min Act: -0.0000

Data Index: 834653 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1930086 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0676. Min Act: -0.0000

Data Index: 357556 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1031355 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1163922 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1232993 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0613. Min Act: -0.0000

Data Index: 555792 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1706297 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0624. Min Act: -0.0000

Data Index: 848777 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0624. Min Act: -0.0000

Data Index: 400484 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1527732 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1779969 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0625. Min Act: -0.0000

Data Index: 422685 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0592. Min Act: -0.0000

Data Index: 264375 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1122271 (The Pile)

Max Activating Token Index: 407