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

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

Neuron 3836 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8430. Min Range: -4.8430

Max Act: 4.8430. Min Act: -0.0001

Data Index: 1299030 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.9293. Min Act: -0.0001

Data Index: 289467 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 4.8430. Min Range: -4.8430

Max Act: 4.0562. Min Act: -0.0001

Data Index: 604999 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.8829. Min Act: -0.0001

Data Index: 1333205 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.8623. Min Act: -0.0001

Data Index: 94849 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.9424. Min Act: -0.0001

Data Index: 1194525 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.7727. Min Act: -0.0001

Data Index: 1262896 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.9385. Min Act: -0.0001

Data Index: 1193662 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.8450. Min Act: -0.0001

Data Index: 146606 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.4820. Min Act: -0.0001

Data Index: 782412 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.5669. Min Act: -0.0001

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.5668. Min Act: -0.0001

Data Index: 193454 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.5063. Min Act: -0.0001

Data Index: 166900 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.3472. Min Act: -0.0001

Data Index: 889017 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.4776. Min Act: -0.0001

Data Index: 867394 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.4420. Min Act: -0.0001

Data Index: 439865 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.4654. Min Act: -0.0001

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.3071. Min Act: -0.0001

Data Index: 345770 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.4585. Min Act: -0.0001

Data Index: 537655 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 4.8430. Min Range: -4.8430

Max Act: 3.2529. Min Act: -0.0001

Data Index: 1336266 (C4 (Web Text))

Max Activating Token Index: 830