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

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

Neuron 4880 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: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0001

Data Index: 104397 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3688. Min Act: -0.0001

Data Index: 648523 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4538. Min Act: -0.0001

Data Index: 556097 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3759. Min Act: -0.0001

Data Index: 890640 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2308. Min Act: -0.0001

Data Index: 459725 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2530. Min Act: -0.0001

Data Index: 458264 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2237. Min Act: -0.0001

Data Index: 606839 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2334. Min Act: -0.0001

Data Index: 865158 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.0627. Min Act: -0.0001

Data Index: 686532 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2131. Min Act: -0.0001

Data Index: 515593 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1729. Min Act: -0.0001

Data Index: 451435 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1951. Min Act: -0.0001

Data Index: 112593 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1458946 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1501. Min Act: -0.0001

Data Index: 264789 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1786. Min Act: -0.0001

Data Index: 606169 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1052135 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.0806. Min Act: -0.0001

Data Index: 1320257 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1564. Min Act: -0.0001

Data Index: 632222 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1080244 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1451. Min Act: -0.0001

Data Index: 1079869 (C4 (Web Text))

Max Activating Token Index: 370