Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 791 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1469217 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1024024 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1205700 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1379330 (Python Code)

Max Activating Token Index: 650

Text #4

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1329607 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1038886 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0466. Min Act: -0.0003

Data Index: 860361 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1490125 (Python Code)

Max Activating Token Index: 891

Text #8

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1517498 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1311443 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1592763 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1447660 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1653657 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0463. Min Act: -0.0003

Data Index: 268575 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1009967 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0480. Min Act: -0.0003

Data Index: 464840 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0461. Min Act: -0.0003

Data Index: 784396 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0479. Min Act: -0.0003

Data Index: 962555 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1097146 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0498. Min Act: -0.0003

Data Index: 862737 (C4 (Web Text))

Max Activating Token Index: 826