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

Dataset: The Pile

Neuron 3968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1074566 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7602. Min Act: -0.0000

Data Index: 845061 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1121416 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7436. Min Act: -0.0000

Data Index: 904204 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1244992 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1824236 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6614. Min Act: -0.0000

Data Index: 976739 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7782. Min Act: -0.0000

Data Index: 159051 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7456. Min Act: -0.0000

Data Index: 901290 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5806. Min Act: -0.0000

Data Index: 150525 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7056. Min Act: -0.0001

Data Index: 570221 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7934. Min Act: -0.0000

Data Index: 179309 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1697168 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1481833 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1102635 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1659618 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1135134 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1212500 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1102964 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1181552 (The Pile)

Max Activating Token Index: 280