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

Dataset: The Pile

Neuron 1176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1145838 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1649704 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3666. Min Act: -0.0000

Data Index: 22797 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1655574 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1392536 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1644357 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3383. Min Act: 0.0000

Data Index: 171356 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1376885 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3311. Min Act: -0.0000

Data Index: 750265 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1341277 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1043744 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1894663 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2981. Min Act: -0.0000

Data Index: 551342 (The Pile)

Max Activating Token Index: 845

Text #13

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2970. Min Act: -0.0000

Data Index: 620316 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1668623 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1580097 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2821. Min Act: -0.0000

Data Index: 491257 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2972. Min Act: -0.0000

Data Index: 325086 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2872. Min Act: 0.0000

Data Index: 411072 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.4415. Min Range: -0.4415

Max Act: 0.2848. Min Act: -0.0000

Data Index: 356227 (The Pile)

Max Activating Token Index: 958