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

Dataset: The Pile

Neuron 1040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1173187 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1982248 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9562. Min Act: -0.0000

Data Index: 354352 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1000361 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1483401 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7501. Min Act: -0.0000

Data Index: 277129 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1445777 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7911. Min Act: -0.0000

Data Index: 325611 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7258. Min Act: -0.0000

Data Index: 459488 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1868294 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7662. Min Act: -0.0000

Data Index: 924598 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1649793 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7166. Min Act: -0.0000

Data Index: 65250 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1538130 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1086377 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7463. Min Act: -0.0000

Data Index: 669027 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7630. Min Act: -0.0000

Data Index: 540498 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7465. Min Act: -0.0000

Data Index: 762025 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7021. Min Act: -0.0000

Data Index: 997434 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1726344 (The Pile)

Max Activating Token Index: 251