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

Dataset: The Pile

Neuron 3957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3497. Min Act: -0.0000

Data Index: 591554 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3579. Min Act: -0.0000

Data Index: 911027 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3571. Min Act: -0.0000

Data Index: 346268 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1607219 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1322691 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1323251 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1074134 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3005. Min Act: -0.0000

Data Index: 210711 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1657951 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3199. Min Act: -0.0000

Data Index: 651060 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2989. Min Act: -0.0000

Data Index: 492397 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1811302 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1976752 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3332. Min Act: -0.0000

Data Index: 852145 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3260. Min Act: -0.0000

Data Index: 233168 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3026. Min Act: -0.0000

Data Index: 330222 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1024256 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1190617 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3145. Min Act: -0.0000

Data Index: 168168 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1562688 (The Pile)

Max Activating Token Index: 230