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

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

Neuron 4812 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9943. Min Act: -0.0000

Data Index: 726770 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.0651. Min Range: -1.0651

Max Act: 1.0651. Min Act: -0.0000

Data Index: 316026 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9968. Min Act: -0.0000

Data Index: 234969 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.0651. Min Range: -1.0651

Max Act: 1.0075. Min Act: -0.0000

Data Index: 661390 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1146964 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1580012 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1053844 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9084. Min Act: -0.0000

Data Index: 285905 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9049. Min Act: -0.0000

Data Index: 371395 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8772. Min Act: -0.0000

Data Index: 129637 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1465733 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8416. Min Act: -0.0000

Data Index: 228796 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1039210 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8749. Min Act: -0.0000

Data Index: 890391 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1432200 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1365034 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8325. Min Act: -0.0000

Data Index: 961876 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1573092 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1405955 (Python Code)

Max Activating Token Index: 578

Text #19

Max Range: 1.0651. Min Range: -1.0651

Max Act: 0.8058. Min Act: -0.0000

Data Index: 981584 (C4 (Web Text))

Max Activating Token Index: 813