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

Dataset: The Pile

Neuron 2980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1979. Min Range: -3.1979

Max Act: 3.1979. Min Act: -0.0000

Data Index: 978270 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 3.1979. Min Range: -3.1979

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1268346 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.1750. Min Act: -0.0000

Data Index: 293151 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.6895. Min Act: -0.0000

Data Index: 199730 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.5946. Min Act: -0.0000

Data Index: 134094 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.4675. Min Act: -0.0000

Data Index: 1779300 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.6607. Min Act: -0.0000

Data Index: 709107 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.2647. Min Act: -0.0000

Data Index: 909923 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.3951. Min Act: -0.0000

Data Index: 1782727 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.2221. Min Act: -0.0000

Data Index: 1259489 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.6127. Min Act: -0.0000

Data Index: 1275741 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.1483. Min Act: -0.0000

Data Index: 645534 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.2586. Min Act: -0.0000

Data Index: 339635 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.3698. Min Act: -0.0000

Data Index: 1609481 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.1881. Min Act: -0.0000

Data Index: 1367083 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1493121 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.0974. Min Act: -0.0000

Data Index: 1115079 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.2074. Min Act: -0.0000

Data Index: 893130 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.4170. Min Act: -0.0000

Data Index: 1030010 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 3.1979. Min Range: -3.1979

Max Act: 2.0767. Min Act: -0.0000

Data Index: 823566 (The Pile)

Max Activating Token Index: 604