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

Dataset: The Pile

Neuron 3579 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: 0.3494. Min Range: -0.3494

Max Act: 0.3320. Min Act: -0.0000

Data Index: 810811 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1341586 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1512656 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1448849 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1959903 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1582464 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3083. Min Act: -0.0000

Data Index: 935675 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2944. Min Act: -0.0000

Data Index: 232460 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1048432 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2916. Min Act: -0.0000

Data Index: 507540 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2906. Min Act: -0.0000

Data Index: 681587 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2874. Min Act: -0.0000

Data Index: 886547 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1881034 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1554964 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1354896 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2563. Min Act: -0.0000

Data Index: 523582 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1439930 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3083. Min Act: -0.0000

Data Index: 431148 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2978. Min Act: -0.0000

Data Index: 841830 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2772. Min Act: -0.0000

Data Index: 34837 (The Pile)

Max Activating Token Index: 531