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

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

Neuron 3282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5946. Min Act: -0.0001

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4496. Min Act: -0.0001

Data Index: 270831 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4966. Min Act: -0.0000

Data Index: 836419 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1275708 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4473. Min Act: -0.0001

Data Index: 186913 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4328. Min Act: -0.0000

Data Index: 74358 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4437. Min Act: -0.0000

Data Index: 771839 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4081. Min Act: -0.0001

Data Index: 244073 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3847. Min Act: -0.0001

Data Index: 163727 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3938. Min Act: -0.0001

Data Index: 639725 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4158. Min Act: -0.0000

Data Index: 88879 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3902. Min Act: -0.0001

Data Index: 312753 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3872. Min Act: -0.0000

Data Index: 351342 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3668. Min Act: -0.0001

Data Index: 207850 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3931. Min Act: -0.0000

Data Index: 8321 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3626. Min Act: -0.0001

Data Index: 953950 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3616. Min Act: -0.0001

Data Index: 1113393 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3857. Min Act: -0.0001

Data Index: 681079 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3636. Min Act: -0.0001

Data Index: 667111 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.3454. Min Act: -0.0001

Data Index: 951505 (C4 (Web Text))

Max Activating Token Index: 491