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

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

Neuron 4036 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: 2.6889. Min Range: -2.6889

Max Act: 2.5901. Min Act: -0.0000

Data Index: 464532 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.4480. Min Act: -0.0000

Data Index: 611419 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.6889. Min Act: -0.0000

Data Index: 524722 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.2626. Min Act: -0.0000

Data Index: 809188 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.1583. Min Act: -0.0000

Data Index: 568050 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.0977. Min Act: -0.0000

Data Index: 1287472 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 2.6889. Min Range: -2.6889

Max Act: 2.1409. Min Act: -0.0000

Data Index: 327809 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.7061. Min Act: -0.0000

Data Index: 884887 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.8245. Min Act: -0.0000

Data Index: 300981 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6967. Min Act: -0.0000

Data Index: 474283 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.7846. Min Act: -0.0000

Data Index: 160200 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6323. Min Act: -0.0000

Data Index: 513140 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6261. Min Act: -0.0000

Data Index: 282690 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.7735. Min Act: -0.0000

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6832. Min Act: -0.0000

Data Index: 69747 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.4790. Min Act: -0.0000

Data Index: 1345067 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6365. Min Act: -0.0000

Data Index: 1040482 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1003761 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6365. Min Act: -0.0000

Data Index: 1127117 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 2.6889. Min Range: -2.6889

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1273818 (C4 (Web Text))

Max Activating Token Index: 159