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

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

Neuron 731 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: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1291836 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1020464 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0556. Min Act: -0.0003

Data Index: 387723 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0535. Min Act: -0.0003

Data Index: 116282 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1351486 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0529. Min Act: -0.0003

Data Index: 300938 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0495. Min Act: -0.0004

Data Index: 1121362 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1117176 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0489. Min Act: -0.0003

Data Index: 386979 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1346408 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0003

Data Index: 819305 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0003

Data Index: 375841 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0476. Min Act: -0.0003

Data Index: 365302 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1044044 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0474. Min Act: -0.0004

Data Index: 866661 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0461. Min Act: -0.0004

Data Index: 1068172 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0463. Min Act: -0.0002

Data Index: 224264 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0468. Min Act: -0.0003

Data Index: 124910 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1278591 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0454. Min Act: -0.0002

Data Index: 587218 (C4 (Web Text))

Max Activating Token Index: 158