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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.1508. Min Act: -0.0002

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.0501. Min Act: -0.0001

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.1508. Min Range: -1.1508

Max Act: 1.0061. Min Act: -0.0002

Data Index: 972899 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8644. Min Act: -0.0001

Data Index: 823488 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.8863. Min Act: -0.0001

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7895. Min Act: -0.0001

Data Index: 665291 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7893. Min Act: -0.0001

Data Index: 803633 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7588. Min Act: -0.0001

Data Index: 799644 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7534. Min Act: -0.0001

Data Index: 1354388 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7970. Min Act: -0.0001

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7667. Min Act: -0.0002

Data Index: 228797 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7917. Min Act: -0.0001

Data Index: 739105 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7200. Min Act: -0.0002

Data Index: 1116631 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7364. Min Act: -0.0002

Data Index: 933689 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.7256. Min Act: -0.0001

Data Index: 1178663 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6890. Min Act: -0.0001

Data Index: 437893 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1224024 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6944. Min Act: -0.0001

Data Index: 860235 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6807. Min Act: -0.0001

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.1508. Min Range: -1.1508

Max Act: 0.6214. Min Act: -0.0002

Data Index: 719685 (C4 (Web Text))

Max Activating Token Index: 984