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

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

Neuron 1676 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1238862 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0546. Min Act: -0.0003

Data Index: 243825 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0492. Min Act: -0.0003

Data Index: 923984 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0529. Min Act: -0.0003

Data Index: 879178 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0509. Min Act: -0.0003

Data Index: 547699 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1284111 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0461. Min Act: -0.0003

Data Index: 232846 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0439. Min Act: -0.0003

Data Index: 507282 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0459. Min Act: -0.0003

Data Index: 947146 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0472. Min Act: -0.0003

Data Index: 123324 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0489. Min Act: -0.0003

Data Index: 586212 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0470. Min Act: -0.0003

Data Index: 825393 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0451. Min Act: -0.0003

Data Index: 361614 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0463. Min Act: -0.0003

Data Index: 293620 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0458. Min Act: -0.0003

Data Index: 750210 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1119867 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0408. Min Act: -0.0003

Data Index: 869066 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0446. Min Act: -0.0003

Data Index: 25605 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1145845 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0412. Min Act: -0.0003

Data Index: 149479 (C4 (Web Text))

Max Activating Token Index: 871