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

Dataset: The Pile

Neuron 1300 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: 1.1942. Min Range: -1.1942

Max Act: 1.1942. Min Act: -0.0000

Data Index: 989641 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8814. Min Act: -0.0000

Data Index: 883467 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 1.1942. Min Range: -1.1942

Max Act: 1.0092. Min Act: -0.0000

Data Index: 29757 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1344840 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1545052 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1826023 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1166121 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8484. Min Act: -0.0000

Data Index: 385300 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8348. Min Act: -0.0000

Data Index: 192265 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8010. Min Act: -0.0000

Data Index: 756477 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7906. Min Act: -0.0000

Data Index: 101784 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.8058. Min Act: -0.0000

Data Index: 281445 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1394709 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1435705 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1482779 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7456. Min Act: -0.0000

Data Index: 95942 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7417. Min Act: -0.0000

Data Index: 371422 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1609359 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7848. Min Act: -0.0000

Data Index: 961333 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 1.1942. Min Range: -1.1942

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1699769 (The Pile)

Max Activating Token Index: 98