Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1687 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2559. Min Act: -0.0002

Data Index: 423240 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3989. Min Act: -0.0001

Data Index: 651893 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2701. Min Act: -0.0002

Data Index: 296319 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3077. Min Act: -0.0001

Data Index: 431111 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3070. Min Act: -0.0002

Data Index: 212312 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2368. Min Act: -0.0002

Data Index: 1086807 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0038. Min Act: -0.0001

Data Index: 170524 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3183. Min Act: -0.0002

Data Index: 468335 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3013. Min Act: -0.0002

Data Index: 632100 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2331. Min Act: -0.0002

Data Index: 796012 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2167. Min Act: -0.0001

Data Index: 902940 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3597. Min Act: -0.0001

Data Index: 306501 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1717. Min Act: -0.0002

Data Index: 534493 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2982. Min Act: -0.0001

Data Index: 577158 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1827. Min Act: -0.0001

Data Index: 718248 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0931. Min Act: -0.0002

Data Index: 932210 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1417. Min Act: -0.0002

Data Index: 426233 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2304. Min Act: -0.0001

Data Index: 1300524 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2329. Min Act: -0.0002

Data Index: 403733 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1294. Min Act: -0.0001

Data Index: 308254 (C4 (Web Text))

Max Activating Token Index: 71