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

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

Neuron 1378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1226381 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.5226. Min Act: -0.0000

Data Index: 599237 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1159053 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4417. Min Act: -0.0000

Data Index: 838016 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4320. Min Act: -0.0001

Data Index: 272492 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4137. Min Act: -0.0000

Data Index: 518682 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4129. Min Act: -0.0000

Data Index: 112847 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4494. Min Act: -0.0000

Data Index: 13960 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3439. Min Act: -0.0001

Data Index: 191341 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1007747 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1287844 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3778. Min Act: -0.0000

Data Index: 612133 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1192867 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3916. Min Act: -0.0000

Data Index: 782557 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1538574 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3815. Min Act: -0.0000

Data Index: 259284 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1250196 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3708. Min Act: -0.0001

Data Index: 1607365 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1065085 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.5226. Min Range: -0.5226

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1125457 (C4 (Web Text))

Max Activating Token Index: 868