Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0212. Min Range: -1.0212

Max Act: 1.0025. Min Act: -0.0000

Data Index: 828330 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.9806. Min Act: -0.0000

Data Index: 345606 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 1.0212. Min Range: -1.0212

Max Act: 1.0212. Min Act: -0.0000

Data Index: 377500 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8609. Min Act: -0.0000

Data Index: 601684 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8582. Min Act: -0.0000

Data Index: 47076 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.9054. Min Act: -0.0000

Data Index: 975660 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8924. Min Act: -0.0000

Data Index: 980582 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8567. Min Act: -0.0000

Data Index: 623685 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8501. Min Act: -0.0000

Data Index: 845294 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.7445. Min Act: -0.0000

Data Index: 218950 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8413. Min Act: -0.0000

Data Index: 613909 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.7500. Min Act: -0.0000

Data Index: 271777 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8347. Min Act: -0.0000

Data Index: 602810 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8284. Min Act: -0.0000

Data Index: 580564 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8175. Min Act: -0.0000

Data Index: 758571 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8208. Min Act: -0.0000

Data Index: 49250 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.8334. Min Act: -0.0000

Data Index: 368632 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.7893. Min Act: -0.0000

Data Index: 414128 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.7661. Min Act: -0.0000

Data Index: 713350 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.0212. Min Range: -1.0212

Max Act: 0.7900. Min Act: -0.0000

Data Index: 658752 (C4 (Web Text))

Max Activating Token Index: 807