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

Dataset: The Pile

Neuron 3330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.4905. Min Act: -0.0000

Data Index: 617379 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1438041 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1566886 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3350. Min Act: -0.0000

Data Index: 789061 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1585804 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1296944 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3695. Min Act: -0.0000

Data Index: 558494 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3443. Min Act: -0.0000

Data Index: 684087 (The Pile)

Max Activating Token Index: 368

Text #8

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2687. Min Act: -0.0000

Data Index: 961306 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1231010 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3425. Min Act: -0.0000

Data Index: 554109 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2457. Min Act: -0.0000

Data Index: 296319 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2366. Min Act: -0.0000

Data Index: 735897 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2258. Min Act: -0.0000

Data Index: 828128 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1284843 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1243158 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2232. Min Act: -0.0000

Data Index: 293745 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3059. Min Act: -0.0000

Data Index: 933076 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1133002 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 1.4905. Min Range: -1.4905

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1134059 (The Pile)

Max Activating Token Index: 653