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

Dataset: The Pile

Neuron 2089 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: 2.1749. Min Range: -2.1749

Max Act: 2.1483. Min Act: -0.0000

Data Index: 1456794 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.1749. Min Act: -0.0000

Data Index: 1442003 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1222779 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.6192. Min Act: -0.0000

Data Index: 1782252 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4752. Min Act: -0.0000

Data Index: 606912 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.5643. Min Act: -0.0000

Data Index: 467811 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4579. Min Act: -0.0000

Data Index: 937990 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1002753 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1512310 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1790463 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1442050 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3465. Min Act: -0.0000

Data Index: 125138 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3862. Min Act: -0.0000

Data Index: 654347 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3842. Min Act: -0.0000

Data Index: 251934 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1204391 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1259670 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1783300 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.3340. Min Act: -0.0000

Data Index: 540783 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1412290 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.2345. Min Act: -0.0000

Data Index: 50361 (The Pile)

Max Activating Token Index: 338