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

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

Neuron 2147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2877. Min Range: -1.2877

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1551514 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.9369. Min Act: -0.0001

Data Index: 1489681 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.7018. Min Act: -0.0001

Data Index: 857281 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1541102 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1509800 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1377010 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1416876 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1425403 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5490. Min Act: -0.0000

Data Index: 119684 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1630822 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1551207 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.5156. Min Act: -0.0001

Data Index: 1590834 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1635729 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4745. Min Act: 0.0000

Data Index: 1458677 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4930. Min Act: -0.0001

Data Index: 640810 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4804. Min Act: -0.0001

Data Index: 1387294 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4427. Min Act: -0.0001

Data Index: 1450430 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4602. Min Act: -0.0001

Data Index: 842674 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1431226 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 1.2877. Min Range: -1.2877

Max Act: 0.4588. Min Act: 0.0000

Data Index: 1537000 (Python Code)

Max Activating Token Index: 82