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

Dataset: The Pile

Neuron 691 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1784615 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6920. Min Act: -0.0000

Data Index: 270311 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.7036. Min Act: 0.0000

Data Index: 151494 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6699. Min Act: -0.0000

Data Index: 77857 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1862678 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6617. Min Act: -0.0000

Data Index: 442311 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1195124 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6440. Min Act: -0.0000

Data Index: 610365 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1552350 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1296722 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1209819 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6238. Min Act: -0.0000

Data Index: 419092 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1254705 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1474328 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1882067 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5982. Min Act: -0.0000

Data Index: 977486 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5963. Min Act: -0.0000

Data Index: 286968 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5985. Min Act: -0.0000

Data Index: 13919 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1109434 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.9428. Min Range: -0.9428

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1338450 (The Pile)

Max Activating Token Index: 79