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

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

Neuron 3550 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: 1.8198. Min Range: -1.8198

Max Act: 1.6096. Min Act: -0.0000

Data Index: 882557 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.8121. Min Act: -0.0000

Data Index: 630704 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4981. Min Act: -0.0000

Data Index: 467592 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.8198. Min Act: -0.0000

Data Index: 243264 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4462. Min Act: -0.0000

Data Index: 153101 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.5700. Min Act: -0.0000

Data Index: 167464 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2824. Min Act: -0.0000

Data Index: 205112 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2399. Min Act: -0.0000

Data Index: 249881 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1199900 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1395052 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2119. Min Act: -0.0000

Data Index: 753143 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2407. Min Act: -0.0000

Data Index: 790441 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2282. Min Act: -0.0000

Data Index: 286297 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2389. Min Act: -0.0000

Data Index: 109496 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2541. Min Act: -0.0000

Data Index: 176759 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1361440 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1006817 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1130828 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3128. Min Act: -0.0000

Data Index: 334088 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.0699. Min Act: -0.0000

Data Index: 50684 (C4 (Web Text))

Max Activating Token Index: 244