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

Dataset: The Pile

Neuron 1989 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: 4.0167. Min Range: -4.0167

Max Act: 4.0167. Min Act: -0.0000

Data Index: 1731178 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.8340. Min Act: -0.0000

Data Index: 883117 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.6636. Min Act: -0.0000

Data Index: 975916 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.6273. Min Act: -0.0000

Data Index: 927605 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.3057. Min Act: -0.0000

Data Index: 1218763 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.2466. Min Act: -0.0000

Data Index: 1529617 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.3097. Min Act: -0.0000

Data Index: 1157212 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1541. Min Act: -0.0000

Data Index: 1255898 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1220. Min Act: -0.0000

Data Index: 551664 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1282. Min Act: -0.0000

Data Index: 70290 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9638. Min Act: -0.0000

Data Index: 24328 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.0922. Min Act: -0.0000

Data Index: 1936199 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.2465. Min Act: -0.0000

Data Index: 1935120 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9432. Min Act: -0.0000

Data Index: 449697 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.0433. Min Act: -0.0000

Data Index: 1931555 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.8871. Min Act: -0.0000

Data Index: 502641 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 4.0167. Min Range: -4.0167

Max Act: 3.1712. Min Act: -0.0000

Data Index: 970157 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9816. Min Act: -0.0000

Data Index: 501201 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9808. Min Act: -0.0000

Data Index: 1877459 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 4.0167. Min Range: -4.0167

Max Act: 2.9567. Min Act: -0.0000

Data Index: 774981 (The Pile)

Max Activating Token Index: 821