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

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

Neuron 4103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3472. Min Act: -0.0000

Data Index: 291120 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2485. Min Act: -0.0000

Data Index: 885064 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3063. Min Act: -0.0000

Data Index: 106556 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2044. Min Act: -0.0000

Data Index: 267735 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1998. Min Act: -0.0000

Data Index: 186878 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1480. Min Act: -0.0000

Data Index: 347915 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1596. Min Act: -0.0000

Data Index: 18440 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1244217 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1255499 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1330. Min Act: -0.0000

Data Index: 698607 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0739. Min Act: -0.0000

Data Index: 286669 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1425. Min Act: -0.0000

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1229. Min Act: -0.0000

Data Index: 626462 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0683. Min Act: -0.0000

Data Index: 183247 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0436. Min Act: -0.0000

Data Index: 798548 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1315956 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0581. Min Act: -0.0000

Data Index: 274146 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0348. Min Act: -0.0000

Data Index: 165827 (C4 (Web Text))

Max Activating Token Index: 216