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

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

Neuron 4297 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.6457. Min Act: -0.0000

Data Index: 713522 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.7719. Min Act: -0.0000

Data Index: 300398 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.4639. Min Act: -0.0000

Data Index: 814053 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.0751. Min Act: -0.0000

Data Index: 1145644 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.2719. Min Act: -0.0000

Data Index: 1270650 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.8944. Min Act: -0.0000

Data Index: 4786 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 8.7719. Min Range: -8.7719

Max Act: 8.0175. Min Act: -0.0000

Data Index: 49841 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.8134. Min Act: -0.0000

Data Index: 946034 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.0167. Min Act: -0.0000

Data Index: 1165190 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.7957. Min Act: -0.0000

Data Index: 384231 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.5383. Min Act: -0.0000

Data Index: 983289 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.6561. Min Act: -0.0000

Data Index: 1286953 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.6504. Min Act: -0.0000

Data Index: 1201797 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.6498. Min Act: -0.0000

Data Index: 737357 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.0373. Min Act: -0.0000

Data Index: 1029668 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.4351. Min Act: -0.0000

Data Index: 812221 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.9059. Min Act: -0.0000

Data Index: 104858 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.1401. Min Act: -0.0000

Data Index: 135915 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.1362. Min Act: -0.0000

Data Index: 731043 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 8.7719. Min Range: -8.7719

Max Act: 7.3124. Min Act: -0.0000

Data Index: 365749 (C4 (Web Text))

Max Activating Token Index: 606