Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1673 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0327. Min Act: -0.0004

Data Index: 722083 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0314. Min Act: -0.0004

Data Index: 192881 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0322. Min Act: -0.0004

Data Index: 172681 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0325. Min Act: -0.0004

Data Index: 341700 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0004

Data Index: 504223 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0291. Min Act: -0.0004

Data Index: 295290 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1257914 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0312. Min Act: -0.0004

Data Index: 812346 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0004

Data Index: 448528 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0308. Min Act: -0.0004

Data Index: 959679 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0312. Min Act: -0.0004

Data Index: 367834 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0004

Data Index: 610323 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0004

Data Index: 931941 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1314320 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0004

Data Index: 586886 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0004

Data Index: 961006 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0287. Min Act: -0.0004

Data Index: 555866 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1004420 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0004

Data Index: 742308 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0280. Min Act: -0.0004

Data Index: 337087 (C4 (Web Text))

Max Activating Token Index: 298