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

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

Neuron 5078 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: 1.5115. Min Range: -1.5115

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1015506 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.1790. Min Act: -0.0000

Data Index: 93842 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.1819. Min Act: -0.0000

Data Index: 660102 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.1487. Min Act: -0.0000

Data Index: 153400 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0748. Min Act: -0.0000

Data Index: 313979 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.5115. Min Range: -1.5115

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1031558 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9966. Min Act: -0.0000

Data Index: 846748 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1069032 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9642. Min Act: -0.0000

Data Index: 91323 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.9428. Min Act: -0.0000

Data Index: 12613 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8893. Min Act: -0.0000

Data Index: 636214 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8923. Min Act: -0.0000

Data Index: 790123 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8711. Min Act: -0.0000

Data Index: 900069 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8622. Min Act: -0.0000

Data Index: 3018 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1102679 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1328732 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8450. Min Act: -0.0000

Data Index: 831165 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.7933. Min Act: -0.0000

Data Index: 727064 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1035159 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.5115. Min Range: -1.5115

Max Act: 0.8451. Min Act: -0.0000

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 124