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

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

Neuron 2895 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1501275 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1391546 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2191. Min Act: -0.0000

Data Index: 168013 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.2379. Min Act: -0.0000

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1482888 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1959. Min Act: -0.0000

Data Index: 229152 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1761. Min Act: -0.0000

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1459622 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0092. Min Act: -0.0000

Data Index: 952409 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1342641 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0448. Min Act: -0.0000

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0435. Min Act: -0.0000

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1466202 (Python Code)

Max Activating Token Index: 830

Text #13

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1188892 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.4975. Min Range: -1.4975

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1373999 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1166352 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1395208 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.4975. Min Range: -1.4975

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1593077 (Python Code)

Max Activating Token Index: 362