Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.5193. Min Act: -0.0000

Data Index: 867693 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1231867 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3518. Min Act: -0.0000

Data Index: 566005 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3823. Min Act: -0.0000

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3664. Min Act: -0.0000

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1303159 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3750. Min Act: -0.0001

Data Index: 973233 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3361. Min Act: -0.0001

Data Index: 360109 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3563. Min Act: -0.0000

Data Index: 200354 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3693. Min Act: -0.0000

Data Index: 901995 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3955. Min Act: -0.0001

Data Index: 693579 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3629. Min Act: -0.0000

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3465. Min Act: -0.0000

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1353242 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3264. Min Act: -0.0000

Data Index: 652414 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3241. Min Act: -0.0000

Data Index: 324335 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.5193. Min Range: -0.5193

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 645