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

Dataset: The Pile

Neuron 2033 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: 0.4552. Min Range: -0.4552

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1262716 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1585167 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.4529. Min Act: 0.0000

Data Index: 265426 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1024740 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3856. Min Act: -0.0000

Data Index: 242325 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1750478 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3652. Min Act: -0.0000

Data Index: 539441 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3548. Min Act: -0.0000

Data Index: 942133 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1446040 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3612. Min Act: -0.0000

Data Index: 787638 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1784489 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1050339 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3238. Min Act: -0.0000

Data Index: 138443 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1717738 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3363. Min Act: -0.0000

Data Index: 621752 (The Pile)

Max Activating Token Index: 268

Text #15

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1666488 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3444. Min Act: -0.0000

Data Index: 39907 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1288723 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1330897 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 0.4552. Min Range: -0.4552

Max Act: 0.3295. Min Act: -0.0000

Data Index: 560665 (The Pile)

Max Activating Token Index: 765