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

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

Neuron 6142 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.0822. Min Act: -0.0002

Data Index: 919656 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1632. Min Act: -0.0001

Data Index: 231439 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.2930. Min Act: -0.0001

Data Index: 1218835 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1845. Min Act: -0.0001

Data Index: 917060 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1797. Min Act: -0.0001

Data Index: 111891 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1169. Min Act: -0.0001

Data Index: 793597 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.2787. Min Act: -0.0001

Data Index: 298801 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1051. Min Act: -0.0001

Data Index: 268696 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.2930. Min Range: -1.2930

Max Act: 0.8809. Min Act: -0.0001

Data Index: 927593 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.0096. Min Act: -0.0001

Data Index: 516335 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.2202. Min Act: -0.0001

Data Index: 693927 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1137. Min Act: -0.0001

Data Index: 232669 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.0623. Min Act: -0.0001

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1875. Min Act: -0.0001

Data Index: 1460026 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 1.2930. Min Range: -1.2930

Max Act: 0.9637. Min Act: -0.0001

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.1710. Min Act: -0.0001

Data Index: 1136783 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.2930. Min Range: -1.2930

Max Act: 1.0880. Min Act: -0.0001

Data Index: 377415 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.2930. Min Range: -1.2930

Max Act: 0.9143. Min Act: -0.0001

Data Index: 282800 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.2930. Min Range: -1.2930

Max Act: 0.9387. Min Act: -0.0001

Data Index: 122040 (C4 (Web Text))

Max Activating Token Index: 115