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

Dataset: The Pile

Neuron 969 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.0658. Min Act: -0.0000

Data Index: 793633 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1383985 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 1.1086. Min Range: -1.1086

Max Act: 1.1086. Min Act: -0.0000

Data Index: 917689 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1104439 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1409588 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1370999 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8842. Min Act: -0.0000

Data Index: 960346 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.9327. Min Act: -0.0000

Data Index: 563489 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8551. Min Act: -0.0000

Data Index: 402289 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1268749 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8339. Min Act: -0.0000

Data Index: 658872 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8833. Min Act: -0.0000

Data Index: 18238 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1146706 (The Pile)

Max Activating Token Index: 495

Text #13

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7800. Min Act: -0.0000

Data Index: 864207 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7810. Min Act: -0.0000

Data Index: 464291 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1993892 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1230527 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.8089. Min Act: -0.0000

Data Index: 916203 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1188527 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.1086. Min Range: -1.1086

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1979948 (The Pile)

Max Activating Token Index: 90