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

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

Neuron 4974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1144. Min Range: -1.1144

Max Act: 1.1144. Min Act: -0.0001

Data Index: 1298831 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.1144. Min Range: -1.1144

Max Act: 1.0590. Min Act: -0.0001

Data Index: 389025 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.1144. Min Range: -1.1144

Max Act: 1.0114. Min Act: -0.0001

Data Index: 729350 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9757. Min Act: -0.0001

Data Index: 567869 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9938. Min Act: -0.0001

Data Index: 558082 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.1144. Min Range: -1.1144

Max Act: 1.0865. Min Act: -0.0001

Data Index: 34715 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1004379 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9750. Min Act: -0.0001

Data Index: 724443 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9862. Min Act: -0.0001

Data Index: 1290945 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9691. Min Act: -0.0001

Data Index: 340359 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.8344. Min Act: -0.0001

Data Index: 906490 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.8985. Min Act: -0.0001

Data Index: 903568 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9822. Min Act: -0.0001

Data Index: 934684 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9316. Min Act: -0.0001

Data Index: 665706 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9284. Min Act: -0.0001

Data Index: 1258558 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.8927. Min Act: -0.0001

Data Index: 1267076 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.8755. Min Act: -0.0001

Data Index: 592576 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9052. Min Act: -0.0001

Data Index: 564203 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.9597. Min Act: -0.0001

Data Index: 1282812 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.1144. Min Range: -1.1144

Max Act: 0.8684. Min Act: -0.0001

Data Index: 612407 (C4 (Web Text))

Max Activating Token Index: 1020