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

Dataset: The Pile

Neuron 2110 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4871. Min Range: -4.4871

Max Act: 4.4871. Min Act: -0.0000

Data Index: 1011586 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.8997. Min Act: -0.0000

Data Index: 975580 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7976. Min Act: -0.0000

Data Index: 964580 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.9406. Min Act: -0.0000

Data Index: 1874230 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.8695. Min Act: -0.0000

Data Index: 950835 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.8419. Min Act: -0.0000

Data Index: 591482 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.8072. Min Act: -0.0000

Data Index: 235348 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7820. Min Act: -0.0000

Data Index: 66527 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7672. Min Act: -0.0000

Data Index: 1685812 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.9404. Min Act: -0.0000

Data Index: 970464 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7105. Min Act: -0.0000

Data Index: 175178 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.8403. Min Act: -0.0000

Data Index: 1219923 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.5140. Min Act: -0.0000

Data Index: 159260 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7960. Min Act: -0.0000

Data Index: 1940531 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.4978. Min Act: -0.0000

Data Index: 271171 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.7804. Min Act: -0.0000

Data Index: 1158427 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.6167. Min Act: -0.0000

Data Index: 793593 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.2861. Min Act: -0.0000

Data Index: 1540799 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.5207. Min Act: -0.0000

Data Index: 871956 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 4.4871. Min Range: -4.4871

Max Act: 3.5108. Min Act: -0.0000

Data Index: 1734996 (The Pile)

Max Activating Token Index: 374