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

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

Neuron 2116 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1376515 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1414948 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1590397 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1628850 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1602016 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.5020. Min Act: 0.0000

Data Index: 1372726 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1575091 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4884. Min Act: -0.0000

Data Index: 759454 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1655751 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1377363 (Python Code)

Max Activating Token Index: 797

Text #10

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4522. Min Act: 0.0000

Data Index: 1401080 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1634257 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4388. Min Act: 0.0000

Data Index: 122008 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1500797 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4127. Min Act: -0.0000

Data Index: 399396 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1405646 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1549589 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1600185 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1579530 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 0.6336. Min Range: -0.6336

Max Act: 0.4475. Min Act: 0.0000

Data Index: 848256 (C4 (Web Text))

Max Activating Token Index: 971