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

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

Neuron 4426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.6164. Min Act: -0.0001

Data Index: 605871 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1464769 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5401. Min Act: -0.0001

Data Index: 1621970 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1362271 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5429. Min Act: -0.0001

Data Index: 1531142 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5468. Min Act: -0.0001

Data Index: 1598184 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1599165 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1133485 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1515412 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5021. Min Act: -0.0001

Data Index: 1493711 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1450786 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1378981 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4956. Min Act: -0.0001

Data Index: 1491374 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4916. Min Act: -0.0001

Data Index: 1640366 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1606958 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4964. Min Act: -0.0001

Data Index: 778304 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4775. Min Act: -0.0001

Data Index: 1501276 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1431313 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4388. Min Act: -0.0001

Data Index: 1420829 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4582. Min Act: -0.0001

Data Index: 1447703 (Python Code)

Max Activating Token Index: 81