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

Dataset: The Pile

Neuron 819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1962188 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7592. Min Act: -0.0000

Data Index: 789145 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1730149 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6357. Min Act: -0.0000

Data Index: 816751 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1163255 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6114. Min Act: -0.0000

Data Index: 883907 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6451. Min Act: -0.0000

Data Index: 773992 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6097. Min Act: -0.0000

Data Index: 963055 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6145. Min Act: -0.0000

Data Index: 82551 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5704. Min Act: -0.0000

Data Index: 435414 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5774. Min Act: -0.0000

Data Index: 10400 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5252. Min Act: -0.0000

Data Index: 563370 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5625. Min Act: -0.0000

Data Index: 847548 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1057161 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5379. Min Act: -0.0000

Data Index: 832575 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1143416 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1424191 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1038114 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5397. Min Act: -0.0000

Data Index: 695380 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1617299 (The Pile)

Max Activating Token Index: 958