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

Dataset: The Pile

Neuron 2861 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3108. Min Range: -1.3108

Max Act: 1.2827. Min Act: -0.0000

Data Index: 759156 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 1.3108. Min Range: -1.3108

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1941879 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 1.3108. Min Range: -1.3108

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1571376 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1607934 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.9484. Min Act: -0.0000

Data Index: 339177 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1253138 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.9310. Min Act: -0.0000

Data Index: 966814 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1771384 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1248091 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1124334 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8549. Min Act: -0.0000

Data Index: 373965 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1094498 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1995711 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8862. Min Act: -0.0000

Data Index: 432825 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8159. Min Act: -0.0000

Data Index: 23959 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1845175 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1063747 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8220. Min Act: -0.0000

Data Index: 522747 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.7935. Min Act: -0.0000

Data Index: 231014 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.3108. Min Range: -1.3108

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1534723 (The Pile)

Max Activating Token Index: 839