Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1043026 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8336. Min Act: -0.0001

Data Index: 1161340 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.9535. Min Act: -0.0001

Data Index: 564161 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7915. Min Act: -0.0002

Data Index: 593936 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6669. Min Act: -0.0002

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8121. Min Act: -0.0002

Data Index: 900199 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.9077. Min Act: -0.0001

Data Index: 337664 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7590. Min Act: -0.0001

Data Index: 367358 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8276. Min Act: -0.0001

Data Index: 211626 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7988. Min Act: -0.0002

Data Index: 1309777 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7671. Min Act: -0.0001

Data Index: 305430 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8691. Min Act: -0.0002

Data Index: 989678 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6452. Min Act: -0.0002

Data Index: 449502 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7560. Min Act: -0.0002

Data Index: 3243 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.8150. Min Act: -0.0002

Data Index: 1300499 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6319. Min Act: -0.0002

Data Index: 463860 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7113. Min Act: -0.0002

Data Index: 53440 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6444. Min Act: -0.0001

Data Index: 984802 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.7123. Min Act: -0.0001

Data Index: 670384 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6445. Min Act: -0.0001

Data Index: 1092287 (C4 (Web Text))

Max Activating Token Index: 558