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

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

Neuron 512 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2652. Min Range: -1.2652

Max Act: 1.2652. Min Act: -0.0000

Data Index: 725284 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.9461. Min Act: 0.0000

Data Index: 1341174 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1075321 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8557. Min Act: -0.0000

Data Index: 57729 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8301. Min Act: 0.0000

Data Index: 284987 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7948. Min Act: -0.0000

Data Index: 361287 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8108. Min Act: -0.0000

Data Index: 942833 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8405. Min Act: -0.0000

Data Index: 144428 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8052. Min Act: -0.0000

Data Index: 85665 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8024. Min Act: -0.0000

Data Index: 963913 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.8253. Min Act: -0.0000

Data Index: 284331 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1229893 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1280273 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7550. Min Act: -0.0000

Data Index: 123884 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7584. Min Act: -0.0000

Data Index: 36139 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7833. Min Act: -0.0000

Data Index: 630467 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7087. Min Act: -0.0000

Data Index: 731579 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7323. Min Act: -0.0000

Data Index: 26746 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7773. Min Act: -0.0000

Data Index: 264573 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.2652. Min Range: -1.2652

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1159533 (C4 (Web Text))

Max Activating Token Index: 905