Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8825. Min Act: -0.0003

Data Index: 7639 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8401. Min Act: -0.0003

Data Index: 191330 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8699. Min Act: -0.0003

Data Index: 1237565 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.9044. Min Act: -0.0003

Data Index: 195559 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8882. Min Act: -0.0003

Data Index: 820167 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8790. Min Act: -0.0003

Data Index: 296811 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8465. Min Act: -0.0003

Data Index: 1359321 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.9176. Min Act: -0.0003

Data Index: 578681 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8279. Min Act: -0.0002

Data Index: 928027 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8505. Min Act: -0.0003

Data Index: 1208509 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8919. Min Act: -0.0003

Data Index: 908972 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8087. Min Act: -0.0003

Data Index: 905866 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8003. Min Act: -0.0003

Data Index: 342816 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.7917. Min Act: -0.0003

Data Index: 880192 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8256. Min Act: -0.0003

Data Index: 358544 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.7723. Min Act: -0.0003

Data Index: 1299458 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.7581. Min Act: -0.0003

Data Index: 465014 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.8268. Min Act: -0.0002

Data Index: 240178 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.6985. Min Act: -0.0003

Data Index: 498560 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.9176. Min Range: -0.9176

Max Act: 0.7925. Min Act: -0.0003

Data Index: 1336431 (C4 (Web Text))

Max Activating Token Index: 779