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

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

Neuron 2458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.7250. Min Act: -0.0000

Data Index: 1482721 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.6959. Min Act: -0.0000

Data Index: 1519672 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.4916. Min Act: -0.0000

Data Index: 1472254 (Python Code)

Max Activating Token Index: 433

Text #3

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.3240. Min Act: -0.0000

Data Index: 1542474 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1574025 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2583. Min Act: -0.0000

Data Index: 1448070 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0965. Min Act: -0.0000

Data Index: 1634042 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1515486 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.1818. Min Act: -0.0000

Data Index: 1415121 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.3222. Min Act: -0.0000

Data Index: 1538210 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1377291 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9609. Min Act: -0.0000

Data Index: 1509072 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0620. Min Act: -0.0000

Data Index: 1488913 (Python Code)

Max Activating Token Index: 471

Text #13

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.8235. Min Act: -0.0000

Data Index: 1646453 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0319. Min Act: -0.0000

Data Index: 1605218 (Python Code)

Max Activating Token Index: 879

Text #15

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1566424 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 2.7250. Min Range: -2.7250

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1526968 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.8075. Min Act: -0.0000

Data Index: 1381889 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.7875. Min Act: -0.0000

Data Index: 1520537 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 2.7250. Min Range: -2.7250

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1622359 (Python Code)

Max Activating Token Index: 217