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

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

Neuron 4350 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: 1.3831. Min Range: -1.3831

Max Act: 1.3831. Min Act: -0.0000

Data Index: 515108 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.3419. Min Act: -0.0000

Data Index: 291797 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9649. Min Act: -0.0000

Data Index: 895602 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9668. Min Act: -0.0000

Data Index: 235934 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9228. Min Act: -0.0000

Data Index: 80911 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8464. Min Act: -0.0000

Data Index: 849581 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9599. Min Act: -0.0000

Data Index: 619453 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8677. Min Act: -0.0000

Data Index: 205383 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8695. Min Act: -0.0000

Data Index: 219096 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8990. Min Act: -0.0000

Data Index: 683862 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8816. Min Act: -0.0000

Data Index: 43333 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8147. Min Act: -0.0000

Data Index: 826191 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8525. Min Act: -0.0000

Data Index: 803572 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8468. Min Act: -0.0000

Data Index: 269334 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8193. Min Act: -0.0000

Data Index: 856139 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1302723 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1286418 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.7991. Min Act: -0.0000

Data Index: 873019 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.7479. Min Act: -0.0000

Data Index: 811996 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.7676. Min Act: -0.0000

Data Index: 493906 (C4 (Web Text))

Max Activating Token Index: 690