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

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

Neuron 4226 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4798. Min Range: -8.4798

Max Act: 8.4798. Min Act: 0.0000

Data Index: 419600 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 8.4798. Min Range: -8.4798

Max Act: 8.0406. Min Act: 0.0000

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 8.4798. Min Range: -8.4798

Max Act: 8.1278. Min Act: -0.0000

Data Index: 951468 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.8734. Min Act: 0.0000

Data Index: 1081033 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.8956. Min Act: 0.0000

Data Index: 799706 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 8.4798. Min Range: -8.4798

Max Act: 8.0587. Min Act: 0.0001

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.5369. Min Act: -0.0000

Data Index: 589030 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.7204. Min Act: -0.0000

Data Index: 415427 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.6654. Min Act: -0.0000

Data Index: 477323 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.6529. Min Act: 0.0000

Data Index: 338373 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.5894. Min Act: -0.0000

Data Index: 282103 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.4428. Min Act: 0.0000

Data Index: 1239286 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.4282. Min Act: 0.0000

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.4282. Min Act: 0.0001

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.5077. Min Act: -0.0000

Data Index: 115609 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.3267. Min Act: 0.0000

Data Index: 400223 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.2992. Min Act: -0.0000

Data Index: 615273 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.2719. Min Act: -0.0000

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.0446. Min Act: 0.0000

Data Index: 1125614 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 8.4798. Min Range: -8.4798

Max Act: 7.0493. Min Act: -0.0000

Data Index: 1335325 (C4 (Web Text))

Max Activating Token Index: 271