Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4590 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.5016. Min Act: -0.0001

Data Index: 68680 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.2762. Min Act: -0.0001

Data Index: 576016 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.3045. Min Act: -0.0001

Data Index: 669307 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.2379. Min Act: -0.0001

Data Index: 472106 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.2151. Min Act: -0.0001

Data Index: 1197067 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1454. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1653. Min Act: -0.0001

Data Index: 481787 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1182. Min Act: -0.0001

Data Index: 1331563 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1109. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1270. Min Act: -0.0001

Data Index: 583192 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1456. Min Act: -0.0001

Data Index: 715676 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.0763. Min Act: -0.0001

Data Index: 797002 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1256. Min Act: -0.0001

Data Index: 902961 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1609. Min Act: -0.0001

Data Index: 991083 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.0477. Min Act: -0.0001

Data Index: 1114141 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.0643. Min Act: -0.0001

Data Index: 665642 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.0325. Min Act: -0.0001

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.1111. Min Act: -0.0001

Data Index: 194267 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.5016. Min Range: -1.5016

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1176085 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.5016. Min Range: -1.5016

Max Act: 0.9074. Min Act: -0.0001

Data Index: 828499 (C4 (Web Text))

Max Activating Token Index: 714