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

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

Neuron 2235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8059. Min Range: -5.8059

Max Act: 5.8059. Min Act: -0.0000

Data Index: 585481 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 5.8059. Min Range: -5.8059

Max Act: 5.1713. Min Act: -0.0000

Data Index: 1131585 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.9666. Min Act: -0.0000

Data Index: 281623 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.7563. Min Act: -0.0000

Data Index: 210357 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.5874. Min Act: -0.0000

Data Index: 1065089 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.7992. Min Act: -0.0000

Data Index: 858594 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.7934. Min Act: -0.0000

Data Index: 385474 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.5218. Min Act: -0.0000

Data Index: 58628 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.7989. Min Act: -0.0000

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.3462. Min Act: -0.0000

Data Index: 1347963 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.2788. Min Act: -0.0000

Data Index: 279675 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.2668. Min Act: -0.0000

Data Index: 158972 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.2310. Min Act: -0.0000

Data Index: 485905 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 5.8059. Min Range: -5.8059

Max Act: 2.9153. Min Act: -0.0000

Data Index: 349859 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.0472. Min Act: -0.0000

Data Index: 265389 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 5.8059. Min Range: -5.8059

Max Act: 2.8858. Min Act: -0.0000

Data Index: 612196 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.1531. Min Act: -0.0000

Data Index: 545183 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 5.8059. Min Range: -5.8059

Max Act: 3.2032. Min Act: -0.0000

Data Index: 854497 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 5.8059. Min Range: -5.8059

Max Act: 2.8923. Min Act: -0.0000

Data Index: 1104061 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 5.8059. Min Range: -5.8059

Max Act: 2.5865. Min Act: -0.0000

Data Index: 931871 (C4 (Web Text))

Max Activating Token Index: 697