Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3988 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5861. Min Act: -0.0001

Data Index: 283525 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5638. Min Act: -0.0001

Data Index: 710826 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5669. Min Act: -0.0001

Data Index: 357715 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5602. Min Act: -0.0001

Data Index: 784697 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5336. Min Act: -0.0001

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5188. Min Act: -0.0001

Data Index: 565616 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5136. Min Act: -0.0001

Data Index: 106009 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1201648 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4972. Min Act: -0.0001

Data Index: 796432 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4886. Min Act: -0.0001

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4569. Min Act: -0.0001

Data Index: 722603 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4497. Min Act: -0.0001

Data Index: 777970 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4887. Min Act: -0.0001

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1141117 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4561. Min Act: -0.0001

Data Index: 197207 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4365. Min Act: -0.0001

Data Index: 446592 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5024. Min Act: -0.0001

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4540. Min Act: -0.0001

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4476. Min Act: -0.0001

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 612