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

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

Neuron 987 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: 0.3669. Min Range: -0.3669

Max Act: 0.3669. Min Act: -0.0001

Data Index: 1261469 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2882. Min Act: -0.0002

Data Index: 1108297 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1170846 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1053905 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2634. Min Act: -0.0002

Data Index: 576342 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2726. Min Act: -0.0001

Data Index: 248661 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2608. Min Act: -0.0002

Data Index: 404876 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2868. Min Act: -0.0002

Data Index: 532640 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2664. Min Act: -0.0002

Data Index: 546755 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2485. Min Act: -0.0002

Data Index: 894831 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2552. Min Act: -0.0001

Data Index: 566719 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2540. Min Act: -0.0001

Data Index: 690176 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2437. Min Act: -0.0002

Data Index: 1103830 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2334. Min Act: -0.0002

Data Index: 1329928 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2492. Min Act: -0.0001

Data Index: 558153 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2420. Min Act: -0.0002

Data Index: 200688 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2369. Min Act: -0.0001

Data Index: 653655 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2455. Min Act: -0.0001

Data Index: 110723 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2402. Min Act: -0.0001

Data Index: 646953 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.3669. Min Range: -0.3669

Max Act: 0.2402. Min Act: -0.0001

Data Index: 581942 (C4 (Web Text))

Max Activating Token Index: 245