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

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

Neuron 1484 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1205580 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1029104 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.4807. Min Act: -0.0000

Data Index: 680299 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.4663. Min Act: -0.0000

Data Index: 481073 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.4115. Min Act: -0.0000

Data Index: 9976 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3765. Min Act: -0.0000

Data Index: 821379 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1355096 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3507. Min Act: -0.0000

Data Index: 535843 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3463. Min Act: -0.0000

Data Index: 367153 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3403. Min Act: -0.0000

Data Index: 471991 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3384. Min Act: -0.0000

Data Index: 552333 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1240257 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.2745. Min Act: -0.0000

Data Index: 471115 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3755. Min Act: -0.0000

Data Index: 486348 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3077. Min Act: -0.0000

Data Index: 573768 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.3116. Min Act: -0.0000

Data Index: 530682 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1353916 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.2162. Min Act: -0.0000

Data Index: 181992 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.2904. Min Act: -0.0000

Data Index: 660957 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 1.7457. Min Range: -1.7457

Max Act: 1.2814. Min Act: -0.0000

Data Index: 347710 (C4 (Web Text))

Max Activating Token Index: 748