Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 93 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5732. Min Act: -0.0001

Data Index: 306255 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.6016. Min Act: -0.0001

Data Index: 691271 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4677. Min Act: -0.0001

Data Index: 654786 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4560. Min Act: -0.0001

Data Index: 932681 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4452. Min Act: -0.0001

Data Index: 1012042 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4734. Min Act: -0.0001

Data Index: 721175 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4272. Min Act: -0.0001

Data Index: 97262 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4315. Min Act: -0.0001

Data Index: 1177486 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4026. Min Act: -0.0001

Data Index: 293556 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3860. Min Act: -0.0001

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4387. Min Act: -0.0001

Data Index: 305765 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4110. Min Act: -0.0001

Data Index: 439524 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4025. Min Act: -0.0001

Data Index: 612054 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1019128 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3860. Min Act: -0.0001

Data Index: 1194841 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4207. Min Act: -0.0001

Data Index: 1053798 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3941. Min Act: -0.0001

Data Index: 654611 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4086. Min Act: -0.0001

Data Index: 852540 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3871. Min Act: -0.0001

Data Index: 540579 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3904. Min Act: -0.0001

Data Index: 1345564 (C4 (Web Text))

Max Activating Token Index: 91