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

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

Neuron 3606 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: 0.2935. Min Range: -0.2935

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1072685 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2829. Min Act: -0.0001

Data Index: 641876 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1357404 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2565. Min Act: -0.0001

Data Index: 661392 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1310988 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2697. Min Act: -0.0001

Data Index: 707057 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2692. Min Act: -0.0001

Data Index: 1002514 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2440. Min Act: -0.0001

Data Index: 852304 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2518. Min Act: -0.0001

Data Index: 495899 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2495. Min Act: -0.0001

Data Index: 11953 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1332676 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2504. Min Act: -0.0001

Data Index: 355015 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1122687 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2577. Min Act: -0.0001

Data Index: 23493 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2442. Min Act: -0.0001

Data Index: 406776 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2402. Min Act: -0.0001

Data Index: 925620 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2333. Min Act: -0.0001

Data Index: 1226507 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1293860 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1310993 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1226284 (C4 (Web Text))

Max Activating Token Index: 443