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

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

Neuron 326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0000

Data Index: 198518 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1398. Min Act: -0.0001

Data Index: 886397 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1186. Min Act: -0.0001

Data Index: 306084 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1132. Min Act: -0.0001

Data Index: 940666 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0971. Min Act: -0.0001

Data Index: 632398 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1076. Min Act: -0.0001

Data Index: 349063 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0884. Min Act: -0.0001

Data Index: 630689 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0998. Min Act: -0.0001

Data Index: 109356 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1015. Min Act: -0.0001

Data Index: 683815 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1162929 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1072. Min Act: -0.0001

Data Index: 513548 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0898. Min Act: -0.0001

Data Index: 687764 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1024. Min Act: -0.0000

Data Index: 528245 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1038. Min Act: -0.0001

Data Index: 786672 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1339240 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0900. Min Act: -0.0001

Data Index: 730128 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1008. Min Act: -0.0001

Data Index: 742557 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1096. Min Act: -0.0001

Data Index: 382405 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0954. Min Act: -0.0001

Data Index: 371877 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1604735 (Python Code)

Max Activating Token Index: 361