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

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

Neuron 4379 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.3944. Min Act: -0.0000

Data Index: 524864 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.3603. Min Act: -0.0000

Data Index: 464739 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.2622. Min Act: -0.0000

Data Index: 466923 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.2349. Min Act: -0.0000

Data Index: 1091708 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.2155. Min Act: -0.0000

Data Index: 734874 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.1829. Min Act: -0.0000

Data Index: 241649 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.1407. Min Act: -0.0000

Data Index: 216290 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.2987. Min Act: -0.0000

Data Index: 187036 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.0616. Min Act: -0.0000

Data Index: 405445 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.8480. Min Act: -0.0000

Data Index: 1196945 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.8430. Min Act: -0.0000

Data Index: 694876 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.9945. Min Act: -0.0000

Data Index: 836118 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.3288. Min Act: -0.0000

Data Index: 120071 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.7963. Min Act: -0.0000

Data Index: 187879 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.8048. Min Act: -0.0000

Data Index: 558267 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 4.3944. Min Range: -4.3944

Max Act: 4.1100. Min Act: -0.0000

Data Index: 44670 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.7585. Min Act: -0.0000

Data Index: 1103005 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.5905. Min Act: -0.0000

Data Index: 447747 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.9452. Min Act: -0.0000

Data Index: 759580 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 4.3944. Min Range: -4.3944

Max Act: 3.8945. Min Act: -0.0000

Data Index: 1307967 (C4 (Web Text))

Max Activating Token Index: 52