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

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

Neuron 2723 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: 0.4888. Min Range: -0.4888

Max Act: 0.4888. Min Act: -0.0001

Data Index: 1651037 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1394993 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4787. Min Act: -0.0001

Data Index: 1436860 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1246568 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1394422 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4469. Min Act: -0.0001

Data Index: 1385537 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1124100 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4305. Min Act: -0.0000

Data Index: 795262 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1609489 (Python Code)

Max Activating Token Index: 300

Text #9

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1487044 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1407422 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1550829 (Python Code)

Max Activating Token Index: 388

Text #12

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1578727 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4126. Min Act: -0.0001

Data Index: 1514827 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3822. Min Act: -0.0001

Data Index: 616457 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1608289 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1220785 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1434446 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1415331 (Python Code)

Max Activating Token Index: 352