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

Dataset: The Pile

Neuron 4098 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: 4.7323. Min Range: -4.7323

Max Act: 4.7323. Min Act: -0.0000

Data Index: 663224 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 4.7323. Min Range: -4.7323

Max Act: 4.3380. Min Act: -0.0000

Data Index: 1635718 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.8522. Min Act: -0.0000

Data Index: 1007423 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.7396. Min Act: -0.0000

Data Index: 72944 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 4.7323. Min Range: -4.7323

Max Act: 4.1678. Min Act: -0.0000

Data Index: 1595457 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.7883. Min Act: -0.0000

Data Index: 564620 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.5796. Min Act: -0.0000

Data Index: 1956827 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.3804. Min Act: -0.0000

Data Index: 485346 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.7936. Min Act: -0.0000

Data Index: 1278907 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.3302. Min Act: -0.0000

Data Index: 1949231 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 4.7323. Min Range: -4.7323

Max Act: 2.9617. Min Act: -0.0000

Data Index: 1800165 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.2878. Min Act: -0.0000

Data Index: 1021750 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.4266. Min Act: -0.0000

Data Index: 588930 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.7175. Min Act: -0.0000

Data Index: 1958931 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.3029. Min Act: -0.0000

Data Index: 318448 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.5854. Min Act: -0.0000

Data Index: 1944027 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 4.7323. Min Range: -4.7323

Max Act: 2.8813. Min Act: -0.0000

Data Index: 930548 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.1143. Min Act: -0.0000

Data Index: 1964890 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 4.7323. Min Range: -4.7323

Max Act: 3.0768. Min Act: -0.0000

Data Index: 1827915 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 4.7323. Min Range: -4.7323

Max Act: 2.8799. Min Act: -0.0000

Data Index: 1257135 (The Pile)

Max Activating Token Index: 751