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

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

Neuron 582 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: 0.4490. Min Range: -0.4490

Max Act: 0.4490. Min Act: -0.0000

Data Index: 287147 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4460. Min Act: -0.0000

Data Index: 413269 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4266. Min Act: -0.0000

Data Index: 895710 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4061. Min Act: -0.0000

Data Index: 69638 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4061. Min Act: -0.0000

Data Index: 476957 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4247. Min Act: -0.0000

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1269555 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4112. Min Act: -0.0000

Data Index: 972904 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.4081. Min Act: -0.0000

Data Index: 50250 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3796. Min Act: -0.0000

Data Index: 221095 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3885. Min Act: -0.0000

Data Index: 116872 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3792. Min Act: -0.0000

Data Index: 425123 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3670. Min Act: -0.0000

Data Index: 17745 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3757. Min Act: -0.0000

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3749. Min Act: 0.0000

Data Index: 770304 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3747. Min Act: -0.0000

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3615. Min Act: -0.0000

Data Index: 61782 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3561. Min Act: -0.0000

Data Index: 112396 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3772. Min Act: -0.0000

Data Index: 65349 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.4490. Min Range: -0.4490

Max Act: 0.3639. Min Act: -0.0000

Data Index: 556477 (C4 (Web Text))

Max Activating Token Index: 251