Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.4537. Min Act: -0.0000

Data Index: 684617 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.3446. Min Act: -0.0000

Data Index: 447705 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.4115. Min Act: -0.0000

Data Index: 244926 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1156122 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.3501. Min Act: -0.0000

Data Index: 250819 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.4131. Min Act: -0.0000

Data Index: 713242 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.3439. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1335. Min Act: -0.0000

Data Index: 93965 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.3880. Min Act: -0.0000

Data Index: 722917 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1005703 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1335818 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.2373. Min Act: -0.0000

Data Index: 836326 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1120714 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1294395 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.2116. Min Act: -0.0000

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1583. Min Act: -0.0000

Data Index: 580059 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1249. Min Act: -0.0000

Data Index: 88209 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1241688 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1350. Min Act: -0.0000

Data Index: 557581 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.4537. Min Range: -1.4537

Max Act: 1.1263. Min Act: -0.0000

Data Index: 724900 (C4 (Web Text))

Max Activating Token Index: 923