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

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

Neuron 1475 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: 1.1237. Min Range: -1.1237

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1127663 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7638. Min Act: -0.0000

Data Index: 489669 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.5632. Min Act: -0.0000

Data Index: 733976 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.5689. Min Act: -0.0000

Data Index: 295979 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.5226. Min Act: -0.0000

Data Index: 550118 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1072142 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4787. Min Act: -0.0000

Data Index: 689440 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4390. Min Act: -0.0000

Data Index: 346950 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4369. Min Act: -0.0000

Data Index: 387515 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4072. Min Act: -0.0000

Data Index: 85458 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4113. Min Act: -0.0000

Data Index: 321215 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3898. Min Act: -0.0000

Data Index: 265759 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4117. Min Act: -0.0000

Data Index: 781111 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3964. Min Act: 0.0000

Data Index: 559939 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1258171 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3781. Min Act: 0.0000

Data Index: 178351 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3827. Min Act: -0.0000

Data Index: 273340 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3790. Min Act: -0.0000

Data Index: 770590 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3816. Min Act: -0.0000

Data Index: 493626 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.3803. Min Act: -0.0000

Data Index: 821019 (C4 (Web Text))

Max Activating Token Index: 1006