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

Dataset: The Pile

Neuron 1716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1194986 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.7131. Min Act: -0.0000

Data Index: 1342453 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.6977. Min Act: -0.0000

Data Index: 1517141 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.5678. Min Act: -0.0000

Data Index: 396159 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1002673 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.4359. Min Act: -0.0000

Data Index: 971532 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1653991 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.4552. Min Act: -0.0000

Data Index: 954876 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1169771 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.3540. Min Act: -0.0000

Data Index: 472713 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.4025. Min Act: -0.0000

Data Index: 955821 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.3400. Min Act: -0.0000

Data Index: 681358 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2985. Min Act: -0.0000

Data Index: 448803 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1518160 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1943316 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2317. Min Act: -0.0000

Data Index: 787261 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.1970. Min Act: -0.0000

Data Index: 874121 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2081. Min Act: -0.0000

Data Index: 777112 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2266. Min Act: -0.0000

Data Index: 800966 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.7131. Min Range: -1.7131

Max Act: 1.2021. Min Act: -0.0000

Data Index: 403955 (The Pile)

Max Activating Token Index: 159