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

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

Neuron 3653 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: 1.1007. Min Range: -1.1007

Max Act: 1.0809. Min Act: -0.0000

Data Index: 228087 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.1007. Min Range: -1.1007

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1325119 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.1007. Min Range: -1.1007

Max Act: 1.0983. Min Act: -0.0000

Data Index: 159093 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.1007. Min Range: -1.1007

Max Act: 1.0225. Min Act: -0.0000

Data Index: 754993 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.1007. Min Range: -1.1007

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1282427 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8887. Min Act: -0.0000

Data Index: 937916 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.9348. Min Act: -0.0000

Data Index: 517852 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.9192. Min Act: -0.0001

Data Index: 552119 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8881. Min Act: -0.0001

Data Index: 440801 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.9201. Min Act: -0.0000

Data Index: 774515 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1244968 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8422. Min Act: -0.0001

Data Index: 746961 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8417. Min Act: -0.0001

Data Index: 270287 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8624. Min Act: -0.0000

Data Index: 394388 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8394. Min Act: -0.0000

Data Index: 437078 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.7729. Min Act: -0.0000

Data Index: 671771 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8325. Min Act: -0.0001

Data Index: 197938 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8582. Min Act: -0.0001

Data Index: 467725 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.7925. Min Act: -0.0000

Data Index: 298801 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.1007. Min Range: -1.1007

Max Act: 0.8149. Min Act: -0.0000

Data Index: 140450 (C4 (Web Text))

Max Activating Token Index: 771