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

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

Neuron 4532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1644. Min Range: -8.1644

Max Act: 8.1644. Min Act: -0.0000

Data Index: 271109 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 8.1644. Min Range: -8.1644

Max Act: 7.8470. Min Act: -0.0000

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 8.1644. Min Range: -8.1644

Max Act: 7.3203. Min Act: 0.0000

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.8747. Min Act: -0.0000

Data Index: 775251 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.8637. Min Act: -0.0000

Data Index: 1132205 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.6603. Min Act: -0.0000

Data Index: 1228679 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.4176. Min Act: -0.0000

Data Index: 152026 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.1671. Min Act: -0.0000

Data Index: 275362 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.3891. Min Act: -0.0000

Data Index: 638615 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.3561. Min Act: -0.0000

Data Index: 915654 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.3418. Min Act: -0.0000

Data Index: 992182 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.3260. Min Act: -0.0000

Data Index: 464682 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.1454. Min Act: -0.0000

Data Index: 78490 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.5050. Min Act: 0.0000

Data Index: 1078022 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.1172. Min Act: -0.0000

Data Index: 100496 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.2733. Min Act: -0.0000

Data Index: 135244 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.4068. Min Act: 0.0000

Data Index: 929574 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.2148. Min Act: -0.0000

Data Index: 271202 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 8.1644. Min Range: -8.1644

Max Act: 6.0441. Min Act: -0.0000

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 8.1644. Min Range: -8.1644

Max Act: 5.8497. Min Act: 0.0000

Data Index: 177481 (C4 (Web Text))

Max Activating Token Index: 753