Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1126150 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0518. Min Act: -0.0002

Data Index: 719141 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0550. Min Act: -0.0002

Data Index: 323657 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1047983 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1434277 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1039833 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0502. Min Act: -0.0002

Data Index: 623652 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0437. Min Act: -0.0001

Data Index: 166042 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0458. Min Act: -0.0002

Data Index: 508337 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0483. Min Act: -0.0002

Data Index: 537186 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0411. Min Act: -0.0002

Data Index: 569880 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0480. Min Act: -0.0002

Data Index: 619062 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0446. Min Act: -0.0001

Data Index: 888872 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0455. Min Act: -0.0002

Data Index: 118988 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0449. Min Act: -0.0002

Data Index: 962762 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0402. Min Act: -0.0002

Data Index: 707645 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1184015 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0555. Min Act: -0.0002

Data Index: 998217 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0358. Min Act: -0.0001

Data Index: 658745 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1156991 (C4 (Web Text))

Max Activating Token Index: 30