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

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

Neuron 3512 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1071492 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6350. Min Act: -0.0000

Data Index: 645923 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5990. Min Act: -0.0000

Data Index: 411829 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5988. Min Act: -0.0000

Data Index: 773458 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5832. Min Act: -0.0000

Data Index: 552263 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5449. Min Act: -0.0000

Data Index: 815940 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1122899 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5090. Min Act: -0.0000

Data Index: 807639 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5004. Min Act: 0.0000

Data Index: 887760 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5159. Min Act: -0.0000

Data Index: 201233 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5178. Min Act: -0.0000

Data Index: 331281 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1092447 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1199965 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1255918 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4552. Min Act: 0.0000

Data Index: 243547 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4834. Min Act: -0.0000

Data Index: 621303 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4840. Min Act: -0.0000

Data Index: 394419 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4561. Min Act: -0.0000

Data Index: 669201 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4685. Min Act: -0.0000

Data Index: 467988 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.4637. Min Act: -0.0000

Data Index: 577479 (C4 (Web Text))

Max Activating Token Index: 174