Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1617 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 11.0031. Min Range: -11.0031

Max Act: 11.0009. Min Act: -0.0000

Data Index: 1344031 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 11.0031. Min Range: -11.0031

Max Act: 11.0031. Min Act: -0.0000

Data Index: 748319 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 11.0031. Min Range: -11.0031

Max Act: 10.4497. Min Act: -0.0000

Data Index: 328334 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 11.0031. Min Range: -11.0031

Max Act: 10.4633. Min Act: -0.0000

Data Index: 634927 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 11.0031. Min Range: -11.0031

Max Act: 10.5966. Min Act: -0.0000

Data Index: 1228479 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.9626. Min Act: -0.0000

Data Index: 1237857 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 11.0031. Min Range: -11.0031

Max Act: 10.2770. Min Act: -0.0000

Data Index: 838165 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.6286. Min Act: -0.0000

Data Index: 536443 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.7168. Min Act: -0.0000

Data Index: 671056 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.0519. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.0289. Min Act: -0.0000

Data Index: 105640 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 11.0031. Min Range: -11.0031

Max Act: 9.0478. Min Act: -0.0000

Data Index: 873584 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 11.0031. Min Range: -11.0031

Max Act: 8.5592. Min Act: -0.0000

Data Index: 1260939 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 11.0031. Min Range: -11.0031

Max Act: 8.2600. Min Act: -0.0000

Data Index: 1313776 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 11.0031. Min Range: -11.0031

Max Act: 8.7622. Min Act: -0.0000

Data Index: 53115 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 11.0031. Min Range: -11.0031

Max Act: 8.9698. Min Act: -0.0000

Data Index: 738005 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 11.0031. Min Range: -11.0031

Max Act: 7.7369. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 11.0031. Min Range: -11.0031

Max Act: 7.6828. Min Act: -0.0000

Data Index: 998654 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 11.0031. Min Range: -11.0031

Max Act: 7.0949. Min Act: -0.0000

Data Index: 1121162 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 11.0031. Min Range: -11.0031

Max Act: 7.3904. Min Act: -0.0000

Data Index: 1220147 (C4 (Web Text))

Max Activating Token Index: 906