Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1440 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2906. Min Act: -0.0001

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2811. Min Act: -0.0001

Data Index: 481172 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2746. Min Act: -0.0001

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2613. Min Act: -0.0001

Data Index: 446698 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2729. Min Act: -0.0001

Data Index: 484155 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2636. Min Act: -0.0001

Data Index: 333888 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2501. Min Act: -0.0001

Data Index: 244325 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2388. Min Act: -0.0001

Data Index: 76258 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2457. Min Act: -0.0001

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2374. Min Act: -0.0001

Data Index: 362908 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2414. Min Act: -0.0001

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2414. Min Act: -0.0001

Data Index: 1241141 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2573. Min Act: -0.0001

Data Index: 1351054 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2578. Min Act: -0.0001

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2658. Min Act: -0.0001

Data Index: 887767 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2398. Min Act: -0.0001

Data Index: 500531 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2638. Min Act: -0.0001

Data Index: 835778 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1054666 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1027225 (C4 (Web Text))

Max Activating Token Index: 930