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

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

Neuron 3677 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6400. Min Range: -2.6400

Max Act: 2.6400. Min Act: -0.0000

Data Index: 200423 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1169362 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.7020. Min Act: -0.0000

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.7801. Min Act: -0.0000

Data Index: 978124 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1069699 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.6572. Min Act: -0.0000

Data Index: 519378 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.6891. Min Act: -0.0000

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.5435. Min Act: -0.0001

Data Index: 231305 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.5462. Min Act: -0.0000

Data Index: 176065 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.4879. Min Act: -0.0000

Data Index: 584832 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.5236. Min Act: -0.0000

Data Index: 886675 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1117588 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.6372. Min Act: -0.0000

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.3840. Min Act: -0.0000

Data Index: 753164 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.4386. Min Act: -0.0000

Data Index: 414676 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1300841 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.4979. Min Act: -0.0000

Data Index: 1129495 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.2743. Min Act: -0.0000

Data Index: 283784 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1133971 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.6400. Min Range: -2.6400

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1210601 (C4 (Web Text))

Max Activating Token Index: 850