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

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

Neuron 5060 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0327. Min Range: -1.0327

Max Act: 1.0327. Min Act: -0.0000

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9583. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1418266 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8992. Min Act: -0.0000

Data Index: 13019 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1571693 (Python Code)

Max Activating Token Index: 346

Text #5

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1426297 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1199675 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8792. Min Act: 0.0001

Data Index: 628127 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7642. Min Act: -0.0000

Data Index: 26493 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8132. Min Act: -0.0000

Data Index: 688244 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7399. Min Act: -0.0000

Data Index: 790313 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1079744 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1154809 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1428866 (Python Code)

Max Activating Token Index: 110

Text #14

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8694. Min Act: -0.0000

Data Index: 458758 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8145. Min Act: 0.0000

Data Index: 568031 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.8095. Min Act: -0.0000

Data Index: 459682 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7483. Min Act: -0.0000

Data Index: 537603 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1053053 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.0327. Min Range: -1.0327

Max Act: 0.7429. Min Act: -0.0000

Data Index: 116429 (C4 (Web Text))

Max Activating Token Index: 337