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

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

Neuron 282 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: 2.0850. Min Range: -2.0850

Max Act: 2.0850. Min Act: -0.0000

Data Index: 1269967 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1019513 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.8403. Min Act: -0.0000

Data Index: 370206 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.9445. Min Act: -0.0000

Data Index: 1331794 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.6979. Min Act: -0.0000

Data Index: 95296 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.5489. Min Act: -0.0000

Data Index: 1056686 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.5424. Min Act: -0.0000

Data Index: 26701 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.4428. Min Act: -0.0000

Data Index: 541274 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.3930. Min Act: -0.0000

Data Index: 934909 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.4262. Min Act: -0.0000

Data Index: 358870 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.5096. Min Act: -0.0000

Data Index: 303427 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.5113. Min Act: -0.0000

Data Index: 124707 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.3822. Min Act: -0.0000

Data Index: 29048 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.3692. Min Act: -0.0000

Data Index: 993075 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2911. Min Act: -0.0000

Data Index: 228269 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2105. Min Act: -0.0000

Data Index: 140076 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2090. Min Act: -0.0000

Data Index: 471124 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1066627 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1038821 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 2.0850. Min Range: -2.0850

Max Act: 1.2363. Min Act: -0.0000

Data Index: 880618 (C4 (Web Text))

Max Activating Token Index: 37