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

Dataset: The Pile

Neuron 1420 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: 3.3602. Min Range: -3.3602

Max Act: 3.3602. Min Act: -0.0000

Data Index: 588502 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1045. Min Act: -0.0000

Data Index: 80018 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 3.3602. Min Range: -3.3602

Max Act: 3.1741. Min Act: -0.0000

Data Index: 901941 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.6972. Min Act: -0.0000

Data Index: 21686 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.2371. Min Act: -0.0000

Data Index: 1640571 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.7651. Min Act: -0.0000

Data Index: 336510 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1175964 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.6356. Min Act: -0.0000

Data Index: 65460 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.8944. Min Act: -0.0000

Data Index: 1685894 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.9150. Min Act: -0.0000

Data Index: 1649261 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.6737. Min Act: -0.0000

Data Index: 1583313 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.8030. Min Act: -0.0000

Data Index: 1462193 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.2274. Min Act: -0.0000

Data Index: 1503301 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1006389 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.7388. Min Act: -0.0000

Data Index: 1383570 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.8714. Min Act: -0.0000

Data Index: 685394 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.4170. Min Act: -0.0000

Data Index: 324194 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.4080. Min Act: -0.0000

Data Index: 737916 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.4716. Min Act: -0.0000

Data Index: 424719 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 3.3602. Min Range: -3.3602

Max Act: 2.8042. Min Act: -0.0000

Data Index: 1259491 (The Pile)

Max Activating Token Index: 794