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

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

Neuron 299 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0739. Min Range: -2.0739

Max Act: 2.0064. Min Act: -0.0001

Data Index: 755350 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 2.0739. Min Range: -2.0739

Max Act: 2.0161. Min Act: -0.0000

Data Index: 749198 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 2.0739. Min Range: -2.0739

Max Act: 2.0739. Min Act: -0.0001

Data Index: 1141779 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.8784. Min Act: -0.0001

Data Index: 777688 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.5311. Min Act: -0.0001

Data Index: 630484 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6773. Min Act: -0.0000

Data Index: 1309405 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6745. Min Act: -0.0001

Data Index: 682365 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.8678. Min Act: -0.0001

Data Index: 792601 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1132158 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.8455. Min Act: -0.0000

Data Index: 916142 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.8441. Min Act: -0.0000

Data Index: 545190 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.5445. Min Act: -0.0001

Data Index: 281097 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1243694 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.7483. Min Act: -0.0000

Data Index: 438127 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.5663. Min Act: -0.0001

Data Index: 1336615 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1172064 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6651. Min Act: -0.0000

Data Index: 352457 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.7272. Min Act: -0.0000

Data Index: 531681 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6269. Min Act: -0.0001

Data Index: 829329 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 2.0739. Min Range: -2.0739

Max Act: 1.6291. Min Act: -0.0000

Data Index: 485296 (C4 (Web Text))

Max Activating Token Index: 485