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

Dataset: The Pile

Neuron 3342 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: 0.1339. Min Range: -0.1339

Max Act: 0.1339. Min Act: -0.0000

Data Index: 732300 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1160413 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1386269 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1290043 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1117167 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1117. Min Act: -0.0000

Data Index: 718102 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1173. Min Act: -0.0000

Data Index: 928793 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1102. Min Act: -0.0000

Data Index: 527544 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1139. Min Act: -0.0000

Data Index: 620662 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1089992 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1058. Min Act: -0.0000

Data Index: 902074 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1417537 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0938. Min Act: -0.0000

Data Index: 575835 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1864335 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.1033. Min Act: -0.0000

Data Index: 661157 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1397911 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1609639 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1971511 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0984. Min Act: -0.0000

Data Index: 936766 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.1339. Min Range: -0.1339

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1812319 (The Pile)

Max Activating Token Index: 268