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

Dataset: The Pile

Neuron 1397 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: 0.6818. Min Range: -0.6818

Max Act: 0.6795. Min Act: -0.0000

Data Index: 990213 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1011020 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0000

Data Index: 273803 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6028. Min Act: -0.0000

Data Index: 376483 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5861. Min Act: -0.0000

Data Index: 273513 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1180689 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5983. Min Act: -0.0000

Data Index: 161428 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6218. Min Act: -0.0000

Data Index: 23922 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1722460 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5948. Min Act: -0.0000

Data Index: 272943 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6136. Min Act: -0.0000

Data Index: 705628 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5970. Min Act: -0.0000

Data Index: 858261 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1265356 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1168400 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1906391 (The Pile)

Max Activating Token Index: 892

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1530308 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1850728 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1577730 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5576. Min Act: -0.0000

Data Index: 192591 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5586. Min Act: -0.0000

Data Index: 935953 (The Pile)

Max Activating Token Index: 150