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

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

Neuron 427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.2957. Min Act: -0.0000

Data Index: 916151 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1348. Min Act: -0.0000

Data Index: 1095591 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.1505. Min Act: -0.0000

Data Index: 1213454 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.2957. Min Range: -3.2957

Max Act: 3.0828. Min Act: -0.0000

Data Index: 125929 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.9337. Min Act: -0.0000

Data Index: 533965 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.8552. Min Act: -0.0000

Data Index: 1040918 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.6455. Min Act: -0.0000

Data Index: 851416 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.9141. Min Act: -0.0000

Data Index: 1206789 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.6364. Min Act: -0.0000

Data Index: 655484 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.7596. Min Act: -0.0000

Data Index: 29160 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.7217. Min Act: -0.0000

Data Index: 77199 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.6455. Min Act: -0.0000

Data Index: 1269693 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1290634 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.4511. Min Act: -0.0000

Data Index: 14127 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.4213. Min Act: -0.0000

Data Index: 1223858 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.5448. Min Act: -0.0000

Data Index: 673120 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.6711. Min Act: -0.0000

Data Index: 888564 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.4965. Min Act: -0.0000

Data Index: 925109 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.3549. Min Act: -0.0000

Data Index: 920062 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 3.2957. Min Range: -3.2957

Max Act: 2.4843. Min Act: -0.0000

Data Index: 259147 (C4 (Web Text))

Max Activating Token Index: 344