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

Dataset: The Pile

Neuron 879 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: 1.5394. Min Range: -1.5394

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1346353 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1707698 (The Pile)

Max Activating Token Index: 861

Text #2

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4979. Min Act: -0.0000

Data Index: 1029141 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.4706. Min Act: -0.0000

Data Index: 411165 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1542163 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1259082 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.2223. Min Act: -0.0000

Data Index: 526810 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1764597 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0846. Min Act: -0.0000

Data Index: 975267 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1772. Min Act: -0.0000

Data Index: 132763 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1021571 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1249888 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1428. Min Act: -0.0000

Data Index: 754265 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0724. Min Act: -0.0000

Data Index: 275164 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0722. Min Act: -0.0000

Data Index: 474554 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1217252 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1147560 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1145. Min Act: -0.0000

Data Index: 316113 (The Pile)

Max Activating Token Index: 289

Text #18

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1351122 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 1.5394. Min Range: -1.5394

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1605840 (The Pile)

Max Activating Token Index: 931