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

Dataset: The Pile

Neuron 2117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4931. Min Act: -0.0000

Data Index: 474709 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1444677 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3730. Min Act: -0.0000

Data Index: 1133918 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.5368. Min Act: -0.0000

Data Index: 272699 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4509. Min Act: -0.0000

Data Index: 1985642 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4140. Min Act: -0.0000

Data Index: 629498 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1595703 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3592. Min Act: -0.0000

Data Index: 652116 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2989. Min Act: -0.0000

Data Index: 413988 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4066. Min Act: -0.0000

Data Index: 589823 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.4256. Min Act: -0.0000

Data Index: 265627 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.3736. Min Act: -0.0000

Data Index: 1061382 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1375461 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2509. Min Act: -0.0000

Data Index: 193130 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2747. Min Act: -0.0000

Data Index: 166996 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1676642 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1912376 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1165064 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.1741. Min Act: -0.0000

Data Index: 804854 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1919117 (The Pile)

Max Activating Token Index: 670