Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1132 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8542. Min Act: -0.0002

Data Index: 753657 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8244. Min Act: -0.0002

Data Index: 993633 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7635. Min Act: -0.0002

Data Index: 1344104 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.8324. Min Act: -0.0002

Data Index: 1186375 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6753. Min Act: -0.0002

Data Index: 85981 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7493. Min Act: -0.0002

Data Index: 727676 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7187. Min Act: -0.0002

Data Index: 854584 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6739. Min Act: -0.0002

Data Index: 222298 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7246. Min Act: -0.0002

Data Index: 588895 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7020. Min Act: -0.0002

Data Index: 228758 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.7224. Min Act: -0.0002

Data Index: 996901 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6814. Min Act: -0.0002

Data Index: 588338 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6676. Min Act: -0.0002

Data Index: 472964 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6639. Min Act: -0.0002

Data Index: 980834 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6174. Min Act: -0.0002

Data Index: 1154205 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6064. Min Act: -0.0002

Data Index: 691264 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.6821. Min Act: -0.0002

Data Index: 101932 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.5452. Min Act: -0.0002

Data Index: 328213 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.5923. Min Act: -0.0002

Data Index: 1287379 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.8542. Min Range: -0.8542

Max Act: 0.5984. Min Act: -0.0002

Data Index: 715606 (C4 (Web Text))

Max Activating Token Index: 307