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

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

Neuron 4814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.6112. Min Act: -0.0000

Data Index: 749207 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.4098. Min Act: -0.0000

Data Index: 287749 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.5272. Min Act: -0.0000

Data Index: 855448 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2452. Min Act: -0.0000

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3623. Min Act: -0.0000

Data Index: 195636 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2202. Min Act: -0.0000

Data Index: 169331 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3588. Min Act: -0.0000

Data Index: 212948 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2369. Min Act: -0.0000

Data Index: 1326556 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3154. Min Act: -0.0000

Data Index: 383704 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.1967. Min Act: -0.0000

Data Index: 721889 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3221. Min Act: -0.0000

Data Index: 1353036 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3559. Min Act: -0.0000

Data Index: 381949 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3513. Min Act: -0.0000

Data Index: 209272 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.1775. Min Act: -0.0000

Data Index: 666309 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.3270. Min Act: -0.0000

Data Index: 194029 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2804. Min Act: -0.0000

Data Index: 307378 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2824. Min Act: -0.0000

Data Index: 1027495 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2667. Min Act: -0.0000

Data Index: 600264 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2474. Min Act: -0.0000

Data Index: 391804 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.6112. Min Range: -3.6112

Max Act: 3.2186. Min Act: -0.0000

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 582