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

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

Neuron 2753 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: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1138847 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5339. Min Act: -0.0000

Data Index: 759313 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1145735 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6094. Min Act: -0.0000

Data Index: 625584 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1547031 (Python Code)

Max Activating Token Index: 853

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4870. Min Act: -0.0000

Data Index: 438843 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1654791 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4939. Min Act: -0.0000

Data Index: 172964 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4544. Min Act: -0.0000

Data Index: 906926 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1441704 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1307089 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1647857 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1251047 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1475832 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1369610 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3470. Min Act: -0.0000

Data Index: 406432 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1287246 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3768. Min Act: -0.0000

Data Index: 297020 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3611. Min Act: -0.0000

Data Index: 683333 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3986. Min Act: -0.0000

Data Index: 484339 (C4 (Web Text))

Max Activating Token Index: 950