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

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

Neuron 3875 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: 3.4141. Min Range: -3.4141

Max Act: 3.4141. Min Act: -0.0001

Data Index: 115698 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.3298. Min Act: -0.0001

Data Index: 75439 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.1154. Min Act: -0.0001

Data Index: 500627 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0252. Min Act: -0.0001

Data Index: 683103 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0198. Min Act: -0.0001

Data Index: 695818 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0869. Min Act: -0.0001

Data Index: 1331526 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0478. Min Act: -0.0001

Data Index: 1150024 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0195. Min Act: -0.0001

Data Index: 533426 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.9594. Min Act: -0.0001

Data Index: 987861 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.9812. Min Act: -0.0001

Data Index: 450885 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.8127. Min Act: -0.0001

Data Index: 55131 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.4141. Min Range: -3.4141

Max Act: 3.0643. Min Act: -0.0001

Data Index: 870153 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.9191. Min Act: -0.0001

Data Index: 13969 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.8712. Min Act: -0.0001

Data Index: 518410 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.8505. Min Act: -0.0001

Data Index: 206857 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.6461. Min Act: -0.0001

Data Index: 1141740 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.6106. Min Act: -0.0001

Data Index: 156578 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.8837. Min Act: -0.0001

Data Index: 564170 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.7491. Min Act: -0.0001

Data Index: 459966 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 3.4141. Min Range: -3.4141

Max Act: 2.7300. Min Act: -0.0001

Data Index: 568818 (C4 (Web Text))

Max Activating Token Index: 916