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

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

Neuron 2966 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: 4.1485. Min Range: -4.1485

Max Act: 4.1485. Min Act: -0.0000

Data Index: 510008 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 4.1485. Min Range: -4.1485

Max Act: 4.0390. Min Act: -0.0000

Data Index: 225811 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 4.1485. Min Range: -4.1485

Max Act: 4.0220. Min Act: -0.0000

Data Index: 1516298 (Python Code)

Max Activating Token Index: 537

Text #3

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.8694. Min Act: -0.0000

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.8504. Min Act: -0.0000

Data Index: 1633524 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.8428. Min Act: -0.0000

Data Index: 943669 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.5508. Min Act: -0.0000

Data Index: 1388545 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.3499. Min Act: -0.0000

Data Index: 986731 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2125. Min Act: -0.0000

Data Index: 757703 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.5231. Min Act: -0.0000

Data Index: 775760 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.3070. Min Act: -0.0000

Data Index: 636537 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2874. Min Act: -0.0000

Data Index: 437821 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.3209. Min Act: -0.0000

Data Index: 226332 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.1255. Min Act: -0.0000

Data Index: 600264 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0902. Min Act: -0.0000

Data Index: 342975 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0520. Min Act: -0.0000

Data Index: 338375 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0557. Min Act: -0.0000

Data Index: 391404 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 4.1485. Min Range: -4.1485

Max Act: 2.9944. Min Act: -0.0000

Data Index: 741153 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0502. Min Act: -0.0000

Data Index: 17898 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 4.1485. Min Range: -4.1485

Max Act: 2.8776. Min Act: -0.0000

Data Index: 319072 (C4 (Web Text))

Max Activating Token Index: 788