Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 442 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1594171 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1656612 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4035. Min Act: -0.0000

Data Index: 734832 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.3742. Min Act: -0.0000

Data Index: 110394 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4064. Min Act: -0.0000

Data Index: 724969 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1723983 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4594. Min Act: -0.0000

Data Index: 497827 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.3241. Min Act: -0.0000

Data Index: 137130 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1025880 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1611788 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2857. Min Act: -0.0000

Data Index: 481114 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2622. Min Act: -0.0000

Data Index: 175935 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1149469 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1286613 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2396. Min Act: -0.0000

Data Index: 627401 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2823. Min Act: -0.0000

Data Index: 761552 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1910633 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1952. Min Act: -0.0000

Data Index: 705549 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1896. Min Act: -0.0000

Data Index: 551618 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.3162. Min Act: -0.0000

Data Index: 700454 (The Pile)

Max Activating Token Index: 729