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

Dataset: The Pile

Neuron 1616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.4468. Min Act: -0.0000

Data Index: 454121 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1350586 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1185166 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3271. Min Act: -0.0000

Data Index: 275600 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3368. Min Act: -0.0000

Data Index: 89673 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1691209 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3208. Min Act: -0.0000

Data Index: 244787 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3297. Min Act: -0.0000

Data Index: 351802 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3270. Min Act: -0.0000

Data Index: 757710 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3035. Min Act: -0.0000

Data Index: 561139 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3195. Min Act: -0.0000

Data Index: 326809 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1615700 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2958. Min Act: -0.0000

Data Index: 839625 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3052. Min Act: -0.0000

Data Index: 551657 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1918535 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2995. Min Act: -0.0000

Data Index: 530811 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3122. Min Act: -0.0000

Data Index: 353191 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3229. Min Act: -0.0000

Data Index: 36093 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1073653 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3020. Min Act: -0.0000

Data Index: 555293 (The Pile)

Max Activating Token Index: 1004