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

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

Neuron 3103 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: 1.6215. Min Range: -1.6215

Max Act: 1.6215. Min Act: -0.0001

Data Index: 854047 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.4508. Min Act: -0.0001

Data Index: 51662 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3909. Min Act: -0.0001

Data Index: 55639 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3566. Min Act: -0.0001

Data Index: 362836 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3041. Min Act: -0.0001

Data Index: 487045 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3225. Min Act: -0.0001

Data Index: 903849 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3552. Min Act: -0.0001

Data Index: 408334 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.3060. Min Act: -0.0001

Data Index: 501520 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2725. Min Act: -0.0001

Data Index: 1291456 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2610. Min Act: -0.0001

Data Index: 837236 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2528. Min Act: -0.0001

Data Index: 877419 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2488. Min Act: -0.0001

Data Index: 984679 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.1680. Min Act: -0.0001

Data Index: 16258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2248. Min Act: -0.0001

Data Index: 831850 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2883. Min Act: -0.0001

Data Index: 1190036 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.1774. Min Act: -0.0001

Data Index: 167738 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2060. Min Act: -0.0001

Data Index: 1304304 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.1577. Min Act: -0.0001

Data Index: 520012 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.2299. Min Act: -0.0001

Data Index: 1095147 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.6215. Min Range: -1.6215

Max Act: 1.1244. Min Act: -0.0001

Data Index: 350868 (C4 (Web Text))

Max Activating Token Index: 642