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

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

Neuron 2599 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.6160. Min Act: -0.0001

Data Index: 291713 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5978. Min Act: -0.0001

Data Index: 608936 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5376. Min Act: -0.0001

Data Index: 914656 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5964. Min Act: -0.0001

Data Index: 519287 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5884. Min Act: -0.0001

Data Index: 661703 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5746. Min Act: -0.0001

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5499. Min Act: -0.0001

Data Index: 115885 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5520. Min Act: -0.0001

Data Index: 247571 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1249112 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5114. Min Act: -0.0001

Data Index: 954315 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5218. Min Act: -0.0001

Data Index: 793750 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5245. Min Act: -0.0001

Data Index: 987454 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5167. Min Act: -0.0001

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5164. Min Act: -0.0001

Data Index: 147582 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5248. Min Act: -0.0001

Data Index: 832754 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5247. Min Act: -0.0001

Data Index: 147287 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1570590 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1317110 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5073. Min Act: -0.0001

Data Index: 114076 (C4 (Web Text))

Max Activating Token Index: 589