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

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

Neuron 3200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.8856. Min Act: -0.0001

Data Index: 490805 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.7826. Min Act: -0.0001

Data Index: 975013 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1001974 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6726. Min Act: -0.0001

Data Index: 627654 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.7000. Min Act: -0.0001

Data Index: 750243 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6962. Min Act: -0.0001

Data Index: 729059 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6484. Min Act: -0.0001

Data Index: 637329 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6101. Min Act: -0.0001

Data Index: 1173020 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1327652 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6257. Min Act: -0.0001

Data Index: 277658 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1273207 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6785. Min Act: -0.0001

Data Index: 1322455 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.6129. Min Act: -0.0001

Data Index: 221649 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5726. Min Act: -0.0001

Data Index: 354884 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5913. Min Act: -0.0001

Data Index: 30777 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1056388 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5792. Min Act: -0.0001

Data Index: 424046 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5535. Min Act: -0.0001

Data Index: 947610 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5566. Min Act: -0.0001

Data Index: 120271 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.8856. Min Range: -0.8856

Max Act: 0.5835. Min Act: -0.0001

Data Index: 573512 (C4 (Web Text))

Max Activating Token Index: 385