Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1732 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0006

Data Index: 1632397 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0480. Min Act: -0.0006

Data Index: 688838 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0488. Min Act: -0.0006

Data Index: 143297 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1175875 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0487. Min Act: -0.0006

Data Index: 637852 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1033588 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0482. Min Act: -0.0006

Data Index: 284968 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0458. Min Act: -0.0006

Data Index: 253720 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0455. Min Act: -0.0006

Data Index: 94032 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0465. Min Act: -0.0006

Data Index: 497837 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1139843 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0439. Min Act: -0.0006

Data Index: 226230 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0483. Min Act: -0.0006

Data Index: 65963 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0495. Min Act: -0.0006

Data Index: 70890 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0474. Min Act: -0.0006

Data Index: 250092 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0464. Min Act: -0.0006

Data Index: 718040 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1577679 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1588677 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0472. Min Act: -0.0006

Data Index: 203406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0479. Min Act: -0.0006

Data Index: 164814 (C4 (Web Text))

Max Activating Token Index: 802