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

Dataset: The Pile

Neuron 3010 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1781738 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1833953 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1926954 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3065. Min Act: -0.0000

Data Index: 421308 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3320. Min Act: -0.0000

Data Index: 565691 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3226. Min Act: -0.0000

Data Index: 472613 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1883110 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2920. Min Act: -0.0000

Data Index: 266592 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1061584 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1168875 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1161369 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1025865 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1589077 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2807. Min Act: -0.0000

Data Index: 773215 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1934959 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2976. Min Act: -0.0000

Data Index: 877808 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1963843 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1757223 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2576. Min Act: -0.0000

Data Index: 232717 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 0.4466. Min Range: -0.4466

Max Act: 0.2671. Min Act: -0.0000

Data Index: 958460 (The Pile)

Max Activating Token Index: 399