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

Dataset: The Pile

Neuron 2048 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: 1.9131. Min Range: -1.9131

Max Act: 1.9131. Min Act: -0.0000

Data Index: 498473 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.8562. Min Act: -0.0000

Data Index: 267259 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1940923 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.7850. Min Act: -0.0000

Data Index: 199385 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1947884 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1849318 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6738. Min Act: -0.0000

Data Index: 275033 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1501146 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.4651. Min Act: -0.0000

Data Index: 741335 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6307. Min Act: -0.0000

Data Index: 1608015 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6102. Min Act: -0.0000

Data Index: 1922747 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6229. Min Act: -0.0000

Data Index: 649888 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.4349. Min Act: -0.0000

Data Index: 395819 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6761. Min Act: -0.0000

Data Index: 392640 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1609311 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6554. Min Act: -0.0000

Data Index: 1919972 (The Pile)

Max Activating Token Index: 717

Text #16

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5541. Min Act: -0.0000

Data Index: 158548 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5224. Min Act: -0.0000

Data Index: 188310 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1604532 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6339. Min Act: -0.0000

Data Index: 327212 (The Pile)

Max Activating Token Index: 128