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

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

Neuron 1375 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: 0.5075. Min Range: -0.5075

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1027605 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3764. Min Act: -0.0001

Data Index: 824597 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3561. Min Act: -0.0001

Data Index: 868527 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3115. Min Act: -0.0001

Data Index: 681602 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2954. Min Act: -0.0001

Data Index: 79709 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3086. Min Act: -0.0001

Data Index: 173830 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1011028 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2581. Min Act: -0.0001

Data Index: 695214 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2582. Min Act: -0.0001

Data Index: 42334 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2661. Min Act: -0.0001

Data Index: 744870 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2638. Min Act: -0.0001

Data Index: 608978 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2718. Min Act: -0.0001

Data Index: 52037 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2701. Min Act: -0.0001

Data Index: 212444 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2361. Min Act: -0.0001

Data Index: 913548 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2495. Min Act: -0.0001

Data Index: 242629 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2546. Min Act: -0.0001

Data Index: 123401 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2576. Min Act: -0.0001

Data Index: 346064 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1136802 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1331000 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.2387. Min Act: -0.0001

Data Index: 788070 (C4 (Web Text))

Max Activating Token Index: 921