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

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

Neuron 1045 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: 2.3023. Min Range: -2.3023

Max Act: 2.3023. Min Act: -0.0000

Data Index: 1167062 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.7943. Min Act: -0.0001

Data Index: 91485 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.5242. Min Act: -0.0000

Data Index: 755026 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.4584. Min Act: -0.0000

Data Index: 1337766 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.5293. Min Act: -0.0000

Data Index: 757760 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1302492 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1174960 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.4068. Min Act: -0.0000

Data Index: 756253 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.2587. Min Act: -0.0000

Data Index: 123183 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1070. Min Act: -0.0000

Data Index: 208690 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.4387. Min Act: -0.0000

Data Index: 33160 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1657. Min Act: -0.0000

Data Index: 195515 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1378. Min Act: -0.0000

Data Index: 267721 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.2269. Min Act: -0.0000

Data Index: 886580 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1937. Min Act: -0.0000

Data Index: 835803 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1356. Min Act: -0.0000

Data Index: 578075 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1180168 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1531. Min Act: -0.0000

Data Index: 205369 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.0931. Min Act: -0.0000

Data Index: 280552 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 2.3023. Min Range: -2.3023

Max Act: 1.1293. Min Act: -0.0000

Data Index: 853011 (C4 (Web Text))

Max Activating Token Index: 980