Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2329 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8192. Min Range: -2.8192

Max Act: 2.8097. Min Act: -0.0001

Data Index: 178857 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 2.8192. Min Range: -2.8192

Max Act: 2.8192. Min Act: -0.0000

Data Index: 532223 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 2.8192. Min Range: -2.8192

Max Act: 2.5519. Min Act: -0.0001

Data Index: 659567 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.8192. Min Range: -2.8192

Max Act: 2.0955. Min Act: -0.0000

Data Index: 138721 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.9747. Min Act: -0.0001

Data Index: 1269116 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.5239. Min Act: -0.0000

Data Index: 885293 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.7658. Min Act: -0.0000

Data Index: 1097180 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.7373. Min Act: -0.0000

Data Index: 727187 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.6074. Min Act: -0.0000

Data Index: 694403 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.6644. Min Act: -0.0000

Data Index: 28788 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1359417 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.5743. Min Act: -0.0000

Data Index: 401063 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.5667. Min Act: -0.0000

Data Index: 513381 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.4785. Min Act: -0.0001

Data Index: 748268 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.4003. Min Act: -0.0001

Data Index: 851340 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.3736. Min Act: -0.0000

Data Index: 827353 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1142072 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.4723. Min Act: -0.0000

Data Index: 657836 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1307319 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 2.8192. Min Range: -2.8192

Max Act: 1.5046. Min Act: -0.0000

Data Index: 766789 (C4 (Web Text))

Max Activating Token Index: 657