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

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

Neuron 3863 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.5334. Min Act: -0.0001

Data Index: 1204976 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.8463. Min Act: -0.0000

Data Index: 1234057 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.4236. Min Act: -0.0001

Data Index: 698053 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.2774. Min Act: -0.0000

Data Index: 473516 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.4663. Min Act: -0.0001

Data Index: 17483 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.1397. Min Act: -0.0000

Data Index: 1173533 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.2483. Min Act: -0.0001

Data Index: 572678 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.2161. Min Act: -0.0000

Data Index: 190992 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.3169. Min Act: -0.0001

Data Index: 835329 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.1691. Min Act: -0.0001

Data Index: 383623 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.2834. Min Act: -0.0000

Data Index: 586860 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.2869. Min Act: -0.0000

Data Index: 910340 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.1695. Min Act: -0.0000

Data Index: 36422 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.1695. Min Act: -0.0000

Data Index: 414701 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.0999. Min Act: -0.0001

Data Index: 467120 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1299639 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.1588. Min Act: -0.0000

Data Index: 32010 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.8463. Min Range: -2.8463

Max Act: 2.0027. Min Act: -0.0000

Data Index: 785292 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 2.8463. Min Range: -2.8463

Max Act: 1.8027. Min Act: -0.0001

Data Index: 306900 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.8463. Min Range: -2.8463

Max Act: 1.9042. Min Act: -0.0000

Data Index: 315702 (C4 (Web Text))

Max Activating Token Index: 249