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

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

Neuron 4473 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4973. Min Range: -2.4973

Max Act: 2.4973. Min Act: -0.0000

Data Index: 965247 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 2.4973. Min Range: -2.4973

Max Act: 2.1726. Min Act: -0.0000

Data Index: 290830 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.6520. Min Act: -0.0000

Data Index: 130225 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.7617. Min Act: -0.0000

Data Index: 957483 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.4203. Min Act: -0.0000

Data Index: 387288 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.5642. Min Act: -0.0000

Data Index: 337509 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.6372. Min Act: -0.0000

Data Index: 898128 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.5443. Min Act: -0.0000

Data Index: 780624 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1280640 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1286864 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.4728. Min Act: -0.0000

Data Index: 741238 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.5066. Min Act: 0.0000

Data Index: 308247 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.4178. Min Act: -0.0000

Data Index: 208003 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.4088. Min Act: -0.0000

Data Index: 394747 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.3707. Min Act: 0.0000

Data Index: 146235 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.4503. Min Act: -0.0000

Data Index: 407104 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.3465. Min Act: 0.0001

Data Index: 639255 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.3277. Min Act: -0.0000

Data Index: 263851 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1057918 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 2.4973. Min Range: -2.4973

Max Act: 1.3017. Min Act: -0.0000

Data Index: 1349416 (C4 (Web Text))

Max Activating Token Index: 354