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

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

Neuron 2529 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7566. Min Range: -7.7566

Max Act: 7.7566. Min Act: -0.0000

Data Index: 487213 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 7.7566. Min Range: -7.7566

Max Act: 5.3979. Min Act: -0.0000

Data Index: 1190977 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 7.7566. Min Range: -7.7566

Max Act: 4.2580. Min Act: -0.0000

Data Index: 484467 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 7.7566. Min Range: -7.7566

Max Act: 4.4629. Min Act: -0.0000

Data Index: 1255671 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 7.7566. Min Range: -7.7566

Max Act: 4.2153. Min Act: -0.0000

Data Index: 498491 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.7363. Min Act: -0.0000

Data Index: 1272213 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.7777. Min Act: -0.0000

Data Index: 237839 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 7.7566. Min Range: -7.7566

Max Act: 4.2522. Min Act: -0.0000

Data Index: 64048 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.8491. Min Act: -0.0000

Data Index: 1233026 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.9647. Min Act: -0.0000

Data Index: 590031 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.7957. Min Act: -0.0000

Data Index: 975910 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.7768. Min Act: -0.0000

Data Index: 883790 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.5508. Min Act: -0.0000

Data Index: 589355 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.3770. Min Act: -0.0000

Data Index: 517797 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.2880. Min Act: -0.0000

Data Index: 603208 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.2219. Min Act: -0.0000

Data Index: 470634 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.0159. Min Act: -0.0000

Data Index: 1239505 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 7.7566. Min Range: -7.7566

Max Act: 2.8508. Min Act: -0.0000

Data Index: 790043 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.0051. Min Act: -0.0000

Data Index: 384015 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 7.7566. Min Range: -7.7566

Max Act: 3.1413. Min Act: -0.0000

Data Index: 1222910 (C4 (Web Text))

Max Activating Token Index: 582