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

Dataset: The Pile

Neuron 2739 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: 0.6751. Min Range: -0.6751

Max Act: 0.6751. Min Act: -0.0000

Data Index: 384750 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6724. Min Act: -0.0000

Data Index: 235332 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6305. Min Act: -0.0000

Data Index: 318676 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6257. Min Act: -0.0000

Data Index: 986413 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1869385 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5850. Min Act: -0.0000

Data Index: 586776 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1996971 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1677321 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5203. Min Act: -0.0000

Data Index: 926102 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5374. Min Act: -0.0000

Data Index: 218547 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5688. Min Act: -0.0000

Data Index: 665950 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5418. Min Act: -0.0000

Data Index: 41586 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5524. Min Act: -0.0000

Data Index: 785922 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1932748 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5710. Min Act: -0.0000

Data Index: 591600 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1087773 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5352. Min Act: -0.0000

Data Index: 35064 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5567. Min Act: -0.0000

Data Index: 913944 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5276. Min Act: 0.0000

Data Index: 1270275 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1923932 (The Pile)

Max Activating Token Index: 133