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

Dataset: The Pile

Neuron 5067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.8049. Min Act: -0.0000

Data Index: 283435 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.8206. Min Act: -0.0000

Data Index: 747554 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7172. Min Act: -0.0000

Data Index: 604821 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1245625 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6284. Min Act: -0.0000

Data Index: 982095 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6729. Min Act: -0.0000

Data Index: 968443 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6483. Min Act: -0.0000

Data Index: 519513 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1318314 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1640037 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6095. Min Act: -0.0000

Data Index: 45627 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5465. Min Act: -0.0000

Data Index: 69314 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1432799 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5094. Min Act: -0.0000

Data Index: 595534 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1185073 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5839. Min Act: -0.0000

Data Index: 71600 (The Pile)

Max Activating Token Index: 931

Text #15

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.4793. Min Act: -0.0000

Data Index: 403392 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1794121 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1690705 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1525932 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5258. Min Act: -0.0000

Data Index: 219675 (The Pile)

Max Activating Token Index: 387