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

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

Neuron 1571 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0001

Data Index: 674193 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1135. Min Act: -0.0001

Data Index: 50723 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1150014 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1254364 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1121543 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1284988 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1430511 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0923. Min Act: -0.0001

Data Index: 673737 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0945. Min Act: -0.0001

Data Index: 337079 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1182654 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1355624 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1042648 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1485252 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1605553 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1637549 (Python Code)

Max Activating Token Index: 596

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1333151 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1207142 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0790. Min Act: -0.0000

Data Index: 224497 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1607430 (Python Code)

Max Activating Token Index: 271