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

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

Neuron 3209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.4126. Min Act: -0.0000

Data Index: 779637 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.6050. Min Act: -0.0000

Data Index: 291031 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1080144 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.4256. Min Act: -0.0000

Data Index: 435207 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1333563 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1281294 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1969. Min Act: -0.0000

Data Index: 908597 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.2761. Min Act: -0.0000

Data Index: 619525 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1720. Min Act: -0.0000

Data Index: 629567 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1165498 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.2178. Min Act: -0.0000

Data Index: 370443 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1035320 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1719. Min Act: -0.0000

Data Index: 159651 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1769. Min Act: -0.0000

Data Index: 300126 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1319027 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1096949 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1316336 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1698. Min Act: -0.0000

Data Index: 605042 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.1102. Min Act: -0.0000

Data Index: 428343 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.6050. Min Range: -1.6050

Max Act: 1.0390. Min Act: -0.0000

Data Index: 902066 (C4 (Web Text))

Max Activating Token Index: 383