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

Dataset: The Pile

Neuron 3800 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: 1.4944. Min Range: -1.4944

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1317673 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1730444 (The Pile)

Max Activating Token Index: 226

Text #2

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.4944. Min Act: -0.0000

Data Index: 229253 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3262. Min Act: -0.0000

Data Index: 750013 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1863380 (The Pile)

Max Activating Token Index: 883

Text #5

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1519. Min Act: -0.0000

Data Index: 658394 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1335294 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.2112. Min Act: -0.0000

Data Index: 39164 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1479919 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1992311 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.2282. Min Act: -0.0000

Data Index: 101111 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1671. Min Act: -0.0000

Data Index: 690783 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1135446 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1568. Min Act: -0.0000

Data Index: 300209 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1072392 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1229. Min Act: -0.0000

Data Index: 424696 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1760065 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1281. Min Act: -0.0000

Data Index: 244869 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1123156 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.1347. Min Act: -0.0000

Data Index: 798080 (The Pile)

Max Activating Token Index: 848