Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 879 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0684. Min Act: -0.0003

Data Index: 1150260 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1139559 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0559. Min Act: -0.0003

Data Index: 931065 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0543. Min Act: -0.0003

Data Index: 512210 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1124280 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0578. Min Act: -0.0003

Data Index: 707707 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0525. Min Act: -0.0003

Data Index: 458224 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1134248 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0499. Min Act: -0.0003

Data Index: 732279 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0487. Min Act: -0.0003

Data Index: 259231 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1156167 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1435002 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1195062 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1188957 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0445. Min Act: -0.0003

Data Index: 319591 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0418. Min Act: -0.0003

Data Index: 665890 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1229298 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0401. Min Act: -0.0004

Data Index: 118165 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0428. Min Act: -0.0003

Data Index: 819490 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0419. Min Act: -0.0003

Data Index: 179267 (C4 (Web Text))

Max Activating Token Index: 222