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

Dataset: The Pile

Neuron 5021 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: 1.3505. Min Range: -1.3505

Max Act: 1.3505. Min Act: 0.0000

Data Index: 509451 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1060680 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9918. Min Act: -0.0000

Data Index: 645674 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8453. Min Act: -0.0000

Data Index: 991256 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1643756 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1243000 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1489008 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1331198 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8477. Min Act: -0.0000

Data Index: 306540 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.6950. Min Act: 0.0000

Data Index: 1845151 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7348. Min Act: -0.0000

Data Index: 401455 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1597419 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7419. Min Act: -0.0000

Data Index: 730597 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7095. Min Act: -0.0000

Data Index: 244510 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1347228 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7410. Min Act: -0.0000

Data Index: 970563 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7327. Min Act: -0.0000

Data Index: 976997 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1461963 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.6830. Min Act: -0.0000

Data Index: 189620 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1476759 (The Pile)

Max Activating Token Index: 444