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

Dataset: The Pile

Neuron 4255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3837. Min Act: -0.0000

Data Index: 853015 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3757. Min Act: -0.0000

Data Index: 728606 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3164. Min Act: -0.0000

Data Index: 970520 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3465. Min Act: -0.0000

Data Index: 566437 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1637591 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1376360 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2330. Min Act: -0.0000

Data Index: 727241 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.3054. Min Act: -0.0000

Data Index: 549487 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2382. Min Act: -0.0000

Data Index: 89623 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2152. Min Act: -0.0000

Data Index: 259311 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1628842 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1415228 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1278545 (The Pile)

Max Activating Token Index: 422

Text #13

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1370771 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1522961 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2851. Min Act: -0.0000

Data Index: 994384 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1158763 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0714. Min Act: -0.0000

Data Index: 449945 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1463163 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 1.3837. Min Range: -1.3837

Max Act: 1.0470. Min Act: -0.0000

Data Index: 883217 (The Pile)

Max Activating Token Index: 869