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

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

Neuron 4566 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: 0.6934. Min Range: -0.6934

Max Act: 0.6934. Min Act: -0.0000

Data Index: 219759 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1087755 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6705. Min Act: -0.0000

Data Index: 47820 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1117304 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1330002 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6166. Min Act: -0.0000

Data Index: 157194 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6218. Min Act: -0.0000

Data Index: 65685 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5949. Min Act: -0.0000

Data Index: 968999 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5883. Min Act: -0.0000

Data Index: 585292 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5841. Min Act: -0.0000

Data Index: 225990 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5879. Min Act: -0.0000

Data Index: 804295 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5656. Min Act: -0.0000

Data Index: 229043 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5626. Min Act: -0.0000

Data Index: 488796 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5883. Min Act: -0.0000

Data Index: 863787 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1321551 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1072155 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5626. Min Act: 0.0001

Data Index: 72858 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5281. Min Act: -0.0000

Data Index: 390538 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5418. Min Act: 0.0000

Data Index: 636989 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5353. Min Act: -0.0000

Data Index: 31141 (C4 (Web Text))

Max Activating Token Index: 459