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

Dataset: The Pile

Neuron 1424 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1184865 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.5258. Min Act: -0.0000

Data Index: 185147 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.6448. Min Act: -0.0000

Data Index: 537860 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1048502 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1454860 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1741366 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1826895 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4362. Min Act: -0.0000

Data Index: 982882 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4220. Min Act: -0.0000

Data Index: 960125 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.3923. Min Act: -0.0000

Data Index: 229915 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.2990. Min Act: -0.0000

Data Index: 691802 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1339950 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4710. Min Act: -0.0000

Data Index: 572287 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4487. Min Act: -0.0000

Data Index: 582957 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.3501. Min Act: -0.0000

Data Index: 939100 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4100. Min Act: -0.0000

Data Index: 578518 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4056. Min Act: -0.0000

Data Index: 390682 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.3105. Min Act: -0.0000

Data Index: 59677 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1620100 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 1.6448. Min Range: -1.6448

Max Act: 1.4001. Min Act: -0.0000

Data Index: 910937 (The Pile)

Max Activating Token Index: 197