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

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

Neuron 5047 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: 0.0690. Min Range: -0.0690

Max Act: 0.0668. Min Act: -0.0000

Data Index: 468008 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0000

Data Index: 338827 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0563. Min Act: -0.0000

Data Index: 1335128 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0557. Min Act: -0.0000

Data Index: 717907 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1026589 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1589183 (Python Code)

Max Activating Token Index: 468

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1146692 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1307587 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1352631 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0489. Min Act: -0.0000

Data Index: 20244 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0514. Min Act: -0.0000

Data Index: 314434 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1376680 (Python Code)

Max Activating Token Index: 651

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0512. Min Act: -0.0000

Data Index: 488521 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1069154 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1431709 (Python Code)

Max Activating Token Index: 652

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0472. Min Act: -0.0000

Data Index: 196546 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0487. Min Act: -0.0000

Data Index: 463542 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1040945 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0565. Min Act: -0.0000

Data Index: 985024 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1133094 (C4 (Web Text))

Max Activating Token Index: 845