Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1593215 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.9052. Min Act: -0.0000

Data Index: 1895143 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.5815. Min Act: -0.0000

Data Index: 1026879 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.5756. Min Act: -0.0000

Data Index: 760702 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2350. Min Act: -0.0000

Data Index: 886936 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.6019. Min Act: -0.0000

Data Index: 419717 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.3970. Min Act: -0.0000

Data Index: 442899 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2711. Min Act: -0.0000

Data Index: 1111503 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2770. Min Act: -0.0000

Data Index: 260314 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.3715. Min Act: -0.0000

Data Index: 485369 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2584. Min Act: -0.0000

Data Index: 1939096 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2127. Min Act: -0.0000

Data Index: 490155 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.2147. Min Act: -0.0000

Data Index: 758131 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.0422. Min Act: -0.0000

Data Index: 228441 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.5074. Min Act: -0.0000

Data Index: 1950477 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 3.1990. Min Range: -3.1990

Max Act: 1.9996. Min Act: -0.0000

Data Index: 1247436 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 3.1990. Min Range: -3.1990

Max Act: 1.8826. Min Act: -0.0000

Data Index: 1307408 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 3.1990. Min Range: -3.1990

Max Act: 1.9816. Min Act: -0.0000

Data Index: 1081972 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.1940. Min Act: -0.0000

Data Index: 110128 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.0828. Min Act: -0.0000

Data Index: 1633181 (The Pile)

Max Activating Token Index: 208