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

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

Neuron 650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1891. Min Act: -0.0000

Data Index: 85974 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1876. Min Act: -0.0000

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1963. Min Act: -0.0000

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1938. Min Act: -0.0000

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1105152 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1446. Min Act: -0.0000

Data Index: 790904 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1011923 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.0873. Min Act: -0.0000

Data Index: 825974 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1207. Min Act: -0.0001

Data Index: 918997 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1279. Min Act: -0.0000

Data Index: 535607 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1158. Min Act: -0.0001

Data Index: 235257 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1113. Min Act: -0.0000

Data Index: 52320 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1134. Min Act: -0.0000

Data Index: 979428 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1042. Min Act: -0.0000

Data Index: 801549 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1128. Min Act: -0.0000

Data Index: 910756 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1269. Min Act: -0.0000

Data Index: 843758 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1311210 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1055964 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1027702 (C4 (Web Text))

Max Activating Token Index: 854