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

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

Neuron 1270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1365. Min Range: -1.1365

Max Act: 1.0637. Min Act: -0.0000

Data Index: 597873 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.1365. Min Range: -1.1365

Max Act: 1.1365. Min Act: -0.0001

Data Index: 960673 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1473230 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 1.1365. Min Range: -1.1365

Max Act: 1.0093. Min Act: -0.0000

Data Index: 606237 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.9155. Min Act: -0.0001

Data Index: 978146 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8575. Min Act: -0.0000

Data Index: 730641 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8806. Min Act: -0.0001

Data Index: 726927 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1064409 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7124. Min Act: -0.0001

Data Index: 585439 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8401. Min Act: -0.0000

Data Index: 442256 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1074122 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7645. Min Act: -0.0001

Data Index: 706948 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.8085. Min Act: -0.0000

Data Index: 39859 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1520202 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1149293 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7942. Min Act: -0.0000

Data Index: 743709 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7077. Min Act: -0.0000

Data Index: 546831 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7318. Min Act: -0.0001

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7728. Min Act: -0.0001

Data Index: 914717 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.1365. Min Range: -1.1365

Max Act: 0.7709. Min Act: -0.0001

Data Index: 687337 (C4 (Web Text))

Max Activating Token Index: 223