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

Dataset: The Pile

Neuron 327 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: 0.9075. Min Range: -0.9075

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1756071 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1213322 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1813917 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1147032 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7840. Min Act: -0.0000

Data Index: 689159 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1647331 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1771539 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7076. Min Act: -0.0000

Data Index: 139383 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1679043 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1146234 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6279. Min Act: -0.0000

Data Index: 58119 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5667. Min Act: -0.0000

Data Index: 321574 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1143059 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5976. Min Act: -0.0000

Data Index: 812607 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5732. Min Act: -0.0000

Data Index: 437544 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5231. Min Act: -0.0000

Data Index: 267770 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1374375 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1127810 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5313. Min Act: -0.0000

Data Index: 703410 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.9075. Min Range: -0.9075

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1801296 (The Pile)

Max Activating Token Index: 427