Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3745 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1334. Min Range: -1.1334

Max Act: 1.0499. Min Act: -0.0001

Data Index: 123410 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.1334. Min Range: -1.1334

Max Act: 1.1334. Min Act: -0.0001

Data Index: 659113 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9903. Min Act: -0.0001

Data Index: 676797 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9205. Min Act: -0.0001

Data Index: 868452 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.1334. Min Range: -1.1334

Max Act: 1.0237. Min Act: -0.0001

Data Index: 861495 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9320. Min Act: -0.0001

Data Index: 135859 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9022. Min Act: -0.0001

Data Index: 284904 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8512. Min Act: -0.0001

Data Index: 244693 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9365. Min Act: -0.0001

Data Index: 366221 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8846. Min Act: -0.0001

Data Index: 1278994 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8489. Min Act: -0.0001

Data Index: 1142194 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8466. Min Act: -0.0001

Data Index: 182952 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8558. Min Act: -0.0001

Data Index: 402178 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7931. Min Act: -0.0001

Data Index: 434044 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8411. Min Act: -0.0001

Data Index: 143607 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7750. Min Act: -0.0001

Data Index: 900559 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8510. Min Act: -0.0001

Data Index: 468808 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8024. Min Act: -0.0001

Data Index: 423172 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7972. Min Act: -0.0001

Data Index: 924375 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8233. Min Act: -0.0001

Data Index: 132685 (C4 (Web Text))

Max Activating Token Index: 681