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

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

Neuron 96 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: 0.3618. Min Range: -0.3618

Max Act: 0.3618. Min Act: -0.0001

Data Index: 1163505 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3201. Min Act: -0.0001

Data Index: 362655 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3042. Min Act: -0.0001

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3215. Min Act: -0.0001

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3321. Min Act: -0.0001

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2760. Min Act: -0.0001

Data Index: 370428 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2820. Min Act: -0.0001

Data Index: 893226 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2588. Min Act: -0.0001

Data Index: 1162950 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2752. Min Act: -0.0001

Data Index: 481942 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2292. Min Act: -0.0001

Data Index: 869257 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1297743 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2726. Min Act: -0.0001

Data Index: 626369 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2466. Min Act: -0.0001

Data Index: 963855 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2405. Min Act: -0.0001

Data Index: 299848 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2563. Min Act: -0.0001

Data Index: 506679 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2520. Min Act: -0.0001

Data Index: 344315 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2513. Min Act: -0.0001

Data Index: 271391 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1134287 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1079594 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2029. Min Act: -0.0001

Data Index: 477441 (C4 (Web Text))

Max Activating Token Index: 856