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

Dataset: The Pile

Neuron 2680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0297. Min Range: -4.0297

Max Act: 4.0297. Min Act: -0.0000

Data Index: 1518971 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.5860. Min Act: -0.0000

Data Index: 737106 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.5679. Min Act: -0.0000

Data Index: 885639 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.5455. Min Act: -0.0000

Data Index: 1054008 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.5057. Min Act: -0.0000

Data Index: 748852 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.4453. Min Act: -0.0000

Data Index: 1321891 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.4226. Min Act: -0.0000

Data Index: 871376 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.5735. Min Act: -0.0000

Data Index: 199251 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.3751. Min Act: -0.0000

Data Index: 1172769 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.3148. Min Act: -0.0000

Data Index: 1254132 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.3086. Min Act: -0.0000

Data Index: 421127 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.2647. Min Act: -0.0000

Data Index: 443009 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.4378. Min Act: -0.0000

Data Index: 1285961 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.2515. Min Act: -0.0000

Data Index: 163318 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.0910. Min Act: -0.0000

Data Index: 514238 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.0272. Min Act: -0.0000

Data Index: 1818127 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.0484. Min Act: -0.0000

Data Index: 683419 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.1782. Min Act: -0.0000

Data Index: 296057 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.1353. Min Act: -0.0000

Data Index: 1279672 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.2983. Min Act: -0.0000

Data Index: 588174 (The Pile)

Max Activating Token Index: 148