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

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

Neuron 2740 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3151. Min Range: -9.3151

Max Act: 9.3151. Min Act: -0.0000

Data Index: 28596 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 9.3151. Min Range: -9.3151

Max Act: 8.9653. Min Act: -0.0000

Data Index: 1287625 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 9.3151. Min Range: -9.3151

Max Act: 8.8120. Min Act: -0.0000

Data Index: 732680 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 9.3151. Min Range: -9.3151

Max Act: 8.6573. Min Act: -0.0000

Data Index: 477920 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 9.3151. Min Range: -9.3151

Max Act: 8.8652. Min Act: -0.0001

Data Index: 837701 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 9.3151. Min Range: -9.3151

Max Act: 8.2695. Min Act: -0.0000

Data Index: 376703 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.9124. Min Act: -0.0000

Data Index: 59380 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.5588. Min Act: -0.0000

Data Index: 317713 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.5466. Min Act: -0.0000

Data Index: 532554 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.8117. Min Act: -0.0000

Data Index: 376119 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.1003. Min Act: -0.0000

Data Index: 1181220 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.3379. Min Act: -0.0001

Data Index: 1311992 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.6944. Min Act: -0.0000

Data Index: 9212 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.5197. Min Act: -0.0000

Data Index: 751682 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 9.3151. Min Range: -9.3151

Max Act: 6.7960. Min Act: -0.0000

Data Index: 376284 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.1462. Min Act: -0.0000

Data Index: 445579 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.2737. Min Act: -0.0000

Data Index: 1122166 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 9.3151. Min Range: -9.3151

Max Act: 6.5481. Min Act: -0.0000

Data Index: 90898 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 9.3151. Min Range: -9.3151

Max Act: 7.4352. Min Act: -0.0000

Data Index: 1054828 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 9.3151. Min Range: -9.3151

Max Act: 6.6974. Min Act: -0.0000

Data Index: 1087109 (C4 (Web Text))

Max Activating Token Index: 817