Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1153752 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.3698. Min Act: -0.0000

Data Index: 1277268 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.3495. Min Act: -0.0000

Data Index: 514357 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1331312 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.3942. Min Act: -0.0000

Data Index: 353170 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.2982. Min Act: -0.0000

Data Index: 986221 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.1638. Min Act: -0.0000

Data Index: 579971 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0673. Min Act: -0.0000

Data Index: 28087 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0162. Min Act: -0.0000

Data Index: 215312 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9671. Min Act: -0.0000

Data Index: 76717 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9905. Min Act: -0.0000

Data Index: 996118 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0369. Min Act: -0.0000

Data Index: 819975 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9451. Min Act: -0.0000

Data Index: 832473 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9639. Min Act: -0.0000

Data Index: 159868 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0232. Min Act: -0.0000

Data Index: 282867 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9549. Min Act: -0.0000

Data Index: 434833 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9839. Min Act: -0.0000

Data Index: 610301 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9787. Min Act: -0.0000

Data Index: 85563 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.5075. Min Range: -1.5075

Max Act: 1.0372. Min Act: -0.0000

Data Index: 336619 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.5075. Min Range: -1.5075

Max Act: 0.9715. Min Act: -0.0000

Data Index: 517476 (C4 (Web Text))

Max Activating Token Index: 541