Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0469. Min Range: -1.0469

Max Act: 1.0469. Min Act: -0.0001

Data Index: 274438 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9272. Min Act: -0.0001

Data Index: 372040 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9001. Min Act: -0.0001

Data Index: 924311 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1137828 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7910. Min Act: -0.0001

Data Index: 1232796 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8953. Min Act: -0.0001

Data Index: 215095 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1327378 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8423. Min Act: -0.0001

Data Index: 762425 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7938. Min Act: -0.0001

Data Index: 966874 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7277. Min Act: -0.0001

Data Index: 683549 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1195342 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7679. Min Act: -0.0001

Data Index: 26913 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6576. Min Act: -0.0001

Data Index: 182770 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6923. Min Act: -0.0001

Data Index: 62223 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6773. Min Act: -0.0001

Data Index: 741640 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1149900 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7467. Min Act: -0.0001

Data Index: 835948 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6812. Min Act: -0.0001

Data Index: 464223 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6375. Min Act: -0.0001

Data Index: 729567 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.6801. Min Act: -0.0000

Data Index: 847561 (C4 (Web Text))

Max Activating Token Index: 854