Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1656 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0561. Min Act: -0.0001

Data Index: 869601 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0603. Min Act: -0.0002

Data Index: 826018 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0510. Min Act: -0.0001

Data Index: 462816 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0002

Data Index: 855264 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0505. Min Act: -0.0001

Data Index: 222188 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0567. Min Act: -0.0002

Data Index: 461001 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0516. Min Act: -0.0002

Data Index: 785970 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0512. Min Act: -0.0002

Data Index: 931632 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1233271 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0565. Min Act: -0.0001

Data Index: 416539 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1011781 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0486. Min Act: -0.0002

Data Index: 339368 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0607. Min Act: -0.0001

Data Index: 268727 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0482. Min Act: -0.0002

Data Index: 745731 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0440. Min Act: -0.0002

Data Index: 943921 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1152512 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0499. Min Act: -0.0002

Data Index: 296974 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1227868 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0472. Min Act: -0.0001

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0486. Min Act: -0.0001

Data Index: 878702 (C4 (Web Text))

Max Activating Token Index: 700