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

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

Neuron 3771 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1052. Min Act: -0.0001

Data Index: 999753 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1188. Min Act: -0.0001

Data Index: 222436 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0001

Data Index: 56687 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1070570 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1438121 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1124. Min Act: -0.0001

Data Index: 859265 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1316596 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1470651 (Python Code)

Max Activating Token Index: 469

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1058. Min Act: -0.0001

Data Index: 133510 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0949. Min Act: -0.0001

Data Index: 753550 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1376405 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1477646 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1088426 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1371044 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0893. Min Act: -0.0001

Data Index: 11445 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1016. Min Act: -0.0001

Data Index: 631399 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1021. Min Act: -0.0001

Data Index: 387062 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0900. Min Act: -0.0001

Data Index: 914745 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1280270 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1438455 (Python Code)

Max Activating Token Index: 312