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

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

Neuron 469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2590. Min Act: -0.0001

Data Index: 365002 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2503. Min Act: -0.0001

Data Index: 671448 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1089322 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2204. Min Act: -0.0001

Data Index: 412748 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2354. Min Act: -0.0001

Data Index: 809051 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2320. Min Act: -0.0001

Data Index: 705017 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2366. Min Act: -0.0001

Data Index: 665446 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2189. Min Act: -0.0001

Data Index: 1133672 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2296. Min Act: -0.0001

Data Index: 300013 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2240. Min Act: -0.0000

Data Index: 254865 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1106647 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1157254 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2219. Min Act: -0.0001

Data Index: 1049775 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2291. Min Act: -0.0001

Data Index: 846544 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2276. Min Act: -0.0001

Data Index: 282925 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2266. Min Act: -0.0001

Data Index: 458665 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2145. Min Act: -0.0001

Data Index: 713924 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2029. Min Act: -0.0000

Data Index: 355581 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2056. Min Act: -0.0001

Data Index: 866098 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1314768 (C4 (Web Text))

Max Activating Token Index: 352