Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4898 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.5090. Min Act: -0.0000

Data Index: 186469 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.5091. Min Act: -0.0000

Data Index: 106815 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4719. Min Act: -0.0000

Data Index: 513915 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1142411 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4151. Min Act: -0.0000

Data Index: 672832 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4479. Min Act: -0.0000

Data Index: 243685 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4663. Min Act: -0.0000

Data Index: 275575 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4256. Min Act: -0.0000

Data Index: 90818 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4285. Min Act: -0.0000

Data Index: 541649 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4230. Min Act: -0.0000

Data Index: 62871 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1220737 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3752. Min Act: -0.0000

Data Index: 567953 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3574. Min Act: -0.0000

Data Index: 712085 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4747. Min Act: -0.0000

Data Index: 446666 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4094. Min Act: -0.0000

Data Index: 443728 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1933 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4072. Min Act: -0.0000

Data Index: 452594 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1269286 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.3570. Min Act: -0.0000

Data Index: 128491 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.5091. Min Range: -0.5091

Max Act: 0.4061. Min Act: -0.0000

Data Index: 468780 (C4 (Web Text))

Max Activating Token Index: 55