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

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

Neuron 4488 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.9002. Min Act: -0.0000

Data Index: 931519 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8419. Min Act: -0.0000

Data Index: 466663 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8450. Min Act: -0.0000

Data Index: 304627 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1342199 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7923. Min Act: -0.0000

Data Index: 790247 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8394. Min Act: -0.0000

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1084447 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1307922 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7993. Min Act: -0.0000

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7619. Min Act: -0.0000

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7513. Min Act: -0.0000

Data Index: 272483 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6907. Min Act: -0.0000

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7134. Min Act: -0.0000

Data Index: 566530 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1191063 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6560. Min Act: -0.0000

Data Index: 150472 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1150206 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1323966 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6592. Min Act: -0.0000

Data Index: 35882 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6770. Min Act: -0.0000

Data Index: 427331 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6622. Min Act: -0.0000

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 530