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

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

Neuron 4312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.7782. Min Act: -0.0001

Data Index: 267820 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.8047. Min Act: -0.0001

Data Index: 23941 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.7681. Min Act: -0.0001

Data Index: 1136382 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.8782. Min Act: -0.0001

Data Index: 907236 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.8112. Min Act: -0.0001

Data Index: 735258 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.7201. Min Act: -0.0001

Data Index: 1210349 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.2650. Min Act: -0.0001

Data Index: 717975 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3488. Min Act: -0.0000

Data Index: 315485 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.0424. Min Act: -0.0001

Data Index: 1047313 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4787. Min Act: -0.0001

Data Index: 74377 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.0099. Min Act: -0.0001

Data Index: 56117 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.1695. Min Act: -0.0001

Data Index: 113648 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.1109. Min Act: -0.0001

Data Index: 1100189 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 3.8782. Min Range: -3.8782

Max Act: 2.9892. Min Act: -0.0001

Data Index: 913757 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.2353. Min Act: -0.0001

Data Index: 558448 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.1249. Min Act: -0.0001

Data Index: 538961 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.0164. Min Act: -0.0001

Data Index: 283701 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3747. Min Act: -0.0001

Data Index: 469336 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 3.8782. Min Range: -3.8782

Max Act: 2.8456. Min Act: -0.0001

Data Index: 1234962 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.8782. Min Range: -3.8782

Max Act: 2.9300. Min Act: -0.0001

Data Index: 167661 (C4 (Web Text))

Max Activating Token Index: 12