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

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

Neuron 1562 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4813. Min Act: -0.0000

Data Index: 543435 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4499. Min Act: -0.0000

Data Index: 938724 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1104429 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1033678 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4130. Min Act: -0.0000

Data Index: 939711 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1588177 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1258154 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3717. Min Act: -0.0000

Data Index: 24604 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1485393 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1174497 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1128687 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3762. Min Act: -0.0000

Data Index: 345544 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1273215 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1528332 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3492. Min Act: -0.0000

Data Index: 113192 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1550284 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1640344 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3563. Min Act: -0.0000

Data Index: 241806 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3587. Min Act: -0.0000

Data Index: 903682 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.4813. Min Range: -0.4813

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1548929 (Python Code)

Max Activating Token Index: 81