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

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

Neuron 6140 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8142. Min Range: -3.8142

Max Act: 3.8142. Min Act: -0.0000

Data Index: 1577389 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 3.8142. Min Range: -3.8142

Max Act: 3.1552. Min Act: -0.0000

Data Index: 1475241 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 3.8142. Min Range: -3.8142

Max Act: 3.2625. Min Act: -0.0000

Data Index: 1624969 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.7199. Min Act: -0.0000

Data Index: 1449770 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.3832. Min Act: -0.0000

Data Index: 1597217 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.4656. Min Act: -0.0000

Data Index: 813540 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.3729. Min Act: -0.0000

Data Index: 1409978 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.0689. Min Act: -0.0000

Data Index: 1454878 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.2766. Min Act: -0.0000

Data Index: 1560255 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.2492. Min Act: -0.0000

Data Index: 725269 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.4051. Min Act: -0.0000

Data Index: 178783 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1464444 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.2460. Min Act: -0.0000

Data Index: 1443850 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1418443 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.2130. Min Act: -0.0000

Data Index: 1640168 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.3181. Min Act: -0.0000

Data Index: 1570045 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.0830. Min Act: -0.0000

Data Index: 974317 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.1835. Min Act: -0.0000

Data Index: 1361318 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.1527. Min Act: -0.0000

Data Index: 1417214 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 3.8142. Min Range: -3.8142

Max Act: 2.2554. Min Act: -0.0000

Data Index: 1610340 (Python Code)

Max Activating Token Index: 57