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

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

Neuron 2091 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: 1.4367. Min Range: -1.4367

Max Act: 1.4367. Min Act: -0.0000

Data Index: 810006 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.2254. Min Act: -0.0001

Data Index: 1626502 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1591585 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.1489. Min Act: -0.0001

Data Index: 1456991 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.2136. Min Act: -0.0001

Data Index: 1639355 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0772. Min Act: -0.0001

Data Index: 1454785 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1362284 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0913. Min Act: -0.0001

Data Index: 1642103 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.1287. Min Act: -0.0001

Data Index: 1391865 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0764. Min Act: -0.0001

Data Index: 1508511 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1455469 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.1023. Min Act: -0.0000

Data Index: 945742 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0265. Min Act: -0.0001

Data Index: 1629476 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.1113. Min Act: -0.0001

Data Index: 1230883 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1580843 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1372845 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 1.4367. Min Range: -1.4367

Max Act: 0.9994. Min Act: -0.0001

Data Index: 1510127 (Python Code)

Max Activating Token Index: 926

Text #17

Max Range: 1.4367. Min Range: -1.4367

Max Act: 0.9887. Min Act: -0.0001

Data Index: 1469804 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 1.4367. Min Range: -1.4367

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1591492 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 1.4367. Min Range: -1.4367

Max Act: 1.0179. Min Act: -0.0001

Data Index: 1440846 (Python Code)

Max Activating Token Index: 978