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

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

Neuron 2622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.7131. Min Act: -0.0001

Data Index: 1029455 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.4237. Min Act: -0.0001

Data Index: 830164 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2350. Min Act: -0.0001

Data Index: 826650 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2587. Min Act: -0.0001

Data Index: 515153 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2618. Min Act: -0.0001

Data Index: 207711 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2095. Min Act: -0.0001

Data Index: 882180 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1876. Min Act: -0.0001

Data Index: 1103478 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2647. Min Act: -0.0001

Data Index: 1189538 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1303395 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1521. Min Act: -0.0001

Data Index: 604576 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1162. Min Act: -0.0001

Data Index: 620641 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1501. Min Act: -0.0001

Data Index: 503647 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2203. Min Act: -0.0001

Data Index: 253529 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.0997. Min Act: -0.0001

Data Index: 522488 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.0645. Min Act: -0.0001

Data Index: 696937 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1510. Min Act: -0.0001

Data Index: 334877 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1138. Min Act: -0.0001

Data Index: 1235842 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.0609. Min Act: -0.0001

Data Index: 821930 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.0881. Min Act: -0.0001

Data Index: 182593 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.0563. Min Act: -0.0001

Data Index: 980094 (C4 (Web Text))

Max Activating Token Index: 98