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

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

Neuron 4882 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: 0.5013. Min Range: -0.5013

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1169364 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1017108 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3755. Min Act: -0.0000

Data Index: 432038 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1237038 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1333604 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3571. Min Act: -0.0000

Data Index: 479129 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3478. Min Act: -0.0000

Data Index: 936574 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1248640 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1035460 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3269. Min Act: -0.0000

Data Index: 949579 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1338965 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3351. Min Act: -0.0000

Data Index: 975858 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3193. Min Act: -0.0000

Data Index: 593725 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1039978 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3125. Min Act: -0.0000

Data Index: 452907 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3016. Min Act: -0.0000

Data Index: 952053 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3065. Min Act: -0.0000

Data Index: 927818 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2919. Min Act: -0.0000

Data Index: 154183 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1114296 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.5013. Min Range: -0.5013

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1133892 (C4 (Web Text))

Max Activating Token Index: 119