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

Dataset: The Pile

Neuron 115 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: 0.3004. Min Range: -0.3004

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1976281 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1479108 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2894. Min Act: -0.0000

Data Index: 13589 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1311276 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2869. Min Act: -0.0000

Data Index: 583753 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1282344 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1124622 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1108187 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1888064 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2746. Min Act: -0.0000

Data Index: 784150 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2753. Min Act: -0.0000

Data Index: 958050 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2693. Min Act: -0.0000

Data Index: 207415 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2699. Min Act: -0.0000

Data Index: 581292 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1657329 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2740. Min Act: -0.0000

Data Index: 716292 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1218188 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2515. Min Act: -0.0000

Data Index: 283198 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2455. Min Act: -0.0000

Data Index: 948006 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1022105 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.3004. Min Range: -0.3004

Max Act: 0.2334. Min Act: -0.0000

Data Index: 636892 (The Pile)

Max Activating Token Index: 334