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

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

Neuron 128 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: 2.1944. Min Range: -2.1944

Max Act: 2.1944. Min Act: -0.0000

Data Index: 674722 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6566. Min Act: -0.0000

Data Index: 822191 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.2949. Min Act: -0.0000

Data Index: 292155 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1252769 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.1578. Min Act: -0.0000

Data Index: 581662 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.2926. Min Act: -0.0000

Data Index: 605838 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.2090. Min Act: -0.0000

Data Index: 527694 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.1218. Min Act: -0.0000

Data Index: 942112 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0435. Min Act: -0.0000

Data Index: 529694 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0910. Min Act: -0.0000

Data Index: 574950 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0336. Min Act: -0.0000

Data Index: 453160 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0933. Min Act: -0.0000

Data Index: 533119 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0922. Min Act: -0.0000

Data Index: 950216 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.1944. Min Range: -2.1944

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1224963 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1215443 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 2.1944. Min Range: -2.1944

Max Act: 0.9888. Min Act: 0.0000

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0389. Min Act: -0.0000

Data Index: 69414 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0317. Min Act: -0.0000

Data Index: 252165 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1330614 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 2.1944. Min Range: -2.1944

Max Act: 0.9918. Min Act: -0.0000

Data Index: 849637 (C4 (Web Text))

Max Activating Token Index: 625