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

Dataset: The Pile

Neuron 1054 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: 0.6488. Min Range: -0.6488

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1781672 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1559514 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1137351 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1029834 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1473347 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1271251 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6171. Min Act: -0.0000

Data Index: 119235 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1372332 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5448. Min Act: -0.0000

Data Index: 724377 (The Pile)

Max Activating Token Index: 861

Text #9

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1949013 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1079656 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1192201 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1222633 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6006. Min Act: -0.0000

Data Index: 599977 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5222. Min Act: 0.0000

Data Index: 93275 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1118231 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5294. Min Act: -0.0000

Data Index: 783039 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1492701 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1665644 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4591. Min Act: -0.0000

Data Index: 904647 (The Pile)

Max Activating Token Index: 456