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

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

Neuron 22 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1631. Min Range: -2.1631

Max Act: 2.1631. Min Act: -0.0000

Data Index: 1640132 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.9493. Min Act: -0.0000

Data Index: 125194 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.9307. Min Act: -0.0000

Data Index: 1008957 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 2.1631. Min Range: -2.1631

Max Act: 2.0198. Min Act: -0.0000

Data Index: 684777 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.8959. Min Act: -0.0000

Data Index: 218758 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7805. Min Act: -0.0000

Data Index: 625508 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6810. Min Act: -0.0000

Data Index: 1626517 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7612. Min Act: -0.0000

Data Index: 1247760 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7435. Min Act: -0.0000

Data Index: 516717 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7387. Min Act: -0.0000

Data Index: 342372 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7186. Min Act: -0.0000

Data Index: 230332 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6263. Min Act: -0.0000

Data Index: 98970 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7062. Min Act: -0.0000

Data Index: 1183043 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7656. Min Act: -0.0000

Data Index: 747389 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1220751 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.5146. Min Act: -0.0000

Data Index: 227936 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1206296 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6074. Min Act: -0.0000

Data Index: 866582 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.5168. Min Act: -0.0000

Data Index: 508365 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 2.1631. Min Range: -2.1631

Max Act: 1.6936. Min Act: -0.0000

Data Index: 78830 (C4 (Web Text))

Max Activating Token Index: 293