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

Dataset: The Pile

Neuron 1939 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: 1.5659. Min Range: -1.5659

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1726634 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2791. Min Act: -0.0000

Data Index: 883584 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.3301. Min Act: -0.0000

Data Index: 766783 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2470. Min Act: -0.0000

Data Index: 1709502 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1306709 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1935137 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.0295. Min Act: -0.0000

Data Index: 243252 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1022891 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1068. Min Act: -0.0000

Data Index: 383668 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1665175 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1812278 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1450910 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9450. Min Act: -0.0000

Data Index: 410772 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1102957 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9535. Min Act: -0.0000

Data Index: 309430 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9149. Min Act: -0.0000

Data Index: 567700 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1009069 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1036622 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9068. Min Act: -0.0000

Data Index: 967039 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 1.5659. Min Range: -1.5659

Max Act: 0.9346. Min Act: -0.0000

Data Index: 401487 (The Pile)

Max Activating Token Index: 534