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

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

Neuron 781 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0777. Min Range: -1.0777

Max Act: 1.0777. Min Act: -0.0000

Data Index: 258969 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.9988. Min Act: -0.0000

Data Index: 732544 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8253. Min Act: -0.0000

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1181319 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7821. Min Act: -0.0001

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7829. Min Act: -0.0000

Data Index: 776367 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1045362 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1259956 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6967. Min Act: -0.0000

Data Index: 832704 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1094959 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6918. Min Act: -0.0000

Data Index: 449750 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1116830 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.7040. Min Act: -0.0000

Data Index: 596758 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1205356 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6112. Min Act: -0.0000

Data Index: 749398 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6570. Min Act: -0.0001

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1057997 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6078. Min Act: -0.0001

Data Index: 1196019 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1020440 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.6563. Min Act: -0.0000

Data Index: 593830 (C4 (Web Text))

Max Activating Token Index: 965