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

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

Neuron 42 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: 0.2839. Min Range: -0.2839

Max Act: 0.2839. Min Act: -0.0001

Data Index: 902710 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2778. Min Act: -0.0001

Data Index: 335671 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2748. Min Act: -0.0001

Data Index: 286676 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1239148 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2627. Min Act: -0.0001

Data Index: 62139 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2620. Min Act: -0.0001

Data Index: 980117 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2570. Min Act: -0.0001

Data Index: 362877 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2658. Min Act: -0.0001

Data Index: 50403 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1177998 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1161474 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2448. Min Act: -0.0001

Data Index: 228640 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2497. Min Act: -0.0001

Data Index: 962217 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2411. Min Act: -0.0001

Data Index: 805333 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1173619 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2315. Min Act: -0.0001

Data Index: 957814 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1126253 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2398. Min Act: -0.0001

Data Index: 446336 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2219. Min Act: -0.0001

Data Index: 474884 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1266554 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2240. Min Act: -0.0001

Data Index: 362376 (C4 (Web Text))

Max Activating Token Index: 59