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

Dataset: The Pile

Neuron 4824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5337. Min Act: -0.0000

Data Index: 154911 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5333. Min Act: -0.0000

Data Index: 883290 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5425. Min Act: -0.0000

Data Index: 887226 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1861672 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1729876 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4954. Min Act: -0.0000

Data Index: 338306 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4464. Min Act: -0.0000

Data Index: 870127 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4145. Min Act: -0.0000

Data Index: 82090 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4109. Min Act: -0.0000

Data Index: 73231 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1747735 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4080. Min Act: -0.0000

Data Index: 117981 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4267. Min Act: -0.0000

Data Index: 691264 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4288. Min Act: -0.0000

Data Index: 783552 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4175. Min Act: -0.0000

Data Index: 769380 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4042. Min Act: -0.0000

Data Index: 614635 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3937. Min Act: -0.0000

Data Index: 606609 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3933. Min Act: -0.0000

Data Index: 991805 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1493946 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3633. Min Act: -0.0000

Data Index: 298350 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1090499 (The Pile)

Max Activating Token Index: 477