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

Dataset: The Pile

Neuron 2025 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.7886. Min Act: -0.0000

Data Index: 1719745 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.8043. Min Act: -0.0000

Data Index: 983858 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.4437. Min Act: -0.0000

Data Index: 475760 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.8043. Min Range: -1.8043

Max Act: 1.0225. Min Act: -0.0000

Data Index: 226985 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8361. Min Act: -0.0000

Data Index: 282871 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1235673 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1724812 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1380682 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1138421 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1858380 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7388. Min Act: -0.0000

Data Index: 591384 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1289709 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1753772 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7913. Min Act: -0.0000

Data Index: 942015 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1938002 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7758. Min Act: -0.0000

Data Index: 916419 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7533. Min Act: -0.0000

Data Index: 764868 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7401. Min Act: 0.0000

Data Index: 530221 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7245. Min Act: -0.0000

Data Index: 408246 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.8043. Min Range: -1.8043

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1015466 (The Pile)

Max Activating Token Index: 81