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

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

Neuron 1321 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: 1.0810. Min Range: -1.0810

Max Act: 1.0082. Min Act: -0.0001

Data Index: 650552 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0810. Min Act: -0.0001

Data Index: 839005 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0133. Min Act: -0.0001

Data Index: 642601 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9329. Min Act: -0.0001

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9382. Min Act: -0.0001

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8926. Min Act: -0.0001

Data Index: 1324290 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1008554 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8694. Min Act: -0.0001

Data Index: 984876 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1294829 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7748. Min Act: -0.0001

Data Index: 949025 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8423. Min Act: -0.0001

Data Index: 759919 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1301722 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8149. Min Act: -0.0001

Data Index: 467306 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8640. Min Act: -0.0001

Data Index: 378178 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8374. Min Act: -0.0001

Data Index: 706309 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8361. Min Act: -0.0001

Data Index: 567886 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8338. Min Act: -0.0001

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7783. Min Act: -0.0001

Data Index: 80964 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.7970. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.8399. Min Act: -0.0001

Data Index: 1130486 (C4 (Web Text))

Max Activating Token Index: 921