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

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

Neuron 1417 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.4109. Min Act: -0.0001

Data Index: 667365 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.1671. Min Act: -0.0001

Data Index: 640600 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.1497. Min Act: -0.0001

Data Index: 687355 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0807. Min Act: -0.0001

Data Index: 505225 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0701. Min Act: -0.0001

Data Index: 554591 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8950. Min Act: -0.0001

Data Index: 1146655 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1229171 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0062. Min Act: -0.0001

Data Index: 307839 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0082. Min Act: -0.0001

Data Index: 650528 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9668. Min Act: -0.0001

Data Index: 1050044 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8296. Min Act: -0.0001

Data Index: 595896 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8937. Min Act: -0.0001

Data Index: 299214 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9144. Min Act: -0.0001

Data Index: 613424 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9964. Min Act: -0.0001

Data Index: 921142 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8610. Min Act: -0.0001

Data Index: 1253580 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8836. Min Act: -0.0001

Data Index: 152248 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9030. Min Act: -0.0001

Data Index: 126961 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9244. Min Act: -0.0001

Data Index: 360120 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8713. Min Act: -0.0001

Data Index: 66312 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9082. Min Act: -0.0002

Data Index: 503886 (C4 (Web Text))

Max Activating Token Index: 160