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

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

Neuron 541 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.6574. Min Act: -0.0001

Data Index: 494520 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.7167. Min Act: -0.0001

Data Index: 550976 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.6805. Min Act: -0.0001

Data Index: 844977 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.6622. Min Act: -0.0001

Data Index: 45919 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.5099. Min Act: -0.0001

Data Index: 1162072 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1223097 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4918. Min Act: -0.0001

Data Index: 671 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4762. Min Act: -0.0001

Data Index: 1074950 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4769. Min Act: -0.0001

Data Index: 616162 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.5030. Min Act: -0.0001

Data Index: 623979 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4676. Min Act: -0.0001

Data Index: 914542 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4252. Min Act: -0.0001

Data Index: 980874 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.3835. Min Act: -0.0001

Data Index: 403693 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1113261 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4033. Min Act: -0.0001

Data Index: 116878 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4442. Min Act: -0.0001

Data Index: 759549 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.3881. Min Act: -0.0001

Data Index: 384509 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4050. Min Act: -0.0001

Data Index: 1018619 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.3569. Min Act: -0.0001

Data Index: 508325 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.7167. Min Range: -0.7167

Max Act: 0.4025. Min Act: -0.0001

Data Index: 125320 (C4 (Web Text))

Max Activating Token Index: 19