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

Dataset: The Pile

Neuron 4246 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: 1.3459. Min Range: -1.3459

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1522757 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.3176. Min Act: -0.0000

Data Index: 229818 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.3056. Min Act: -0.0000

Data Index: 118307 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2929. Min Act: -0.0000

Data Index: 503191 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1546140 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2854. Min Act: -0.0000

Data Index: 330902 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1366342 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1188678 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1914. Min Act: -0.0000

Data Index: 537018 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2626. Min Act: -0.0000

Data Index: 1001986 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2100. Min Act: -0.0000

Data Index: 963704 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2140. Min Act: -0.0000

Data Index: 390778 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1486. Min Act: -0.0000

Data Index: 884152 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1927526 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.2025. Min Act: -0.0000

Data Index: 162728 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1309. Min Act: -0.0000

Data Index: 487260 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1589722 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.3251. Min Act: -0.0000

Data Index: 563290 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1968566 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.3459. Min Range: -1.3459

Max Act: 1.1062. Min Act: -0.0000

Data Index: 381135 (The Pile)

Max Activating Token Index: 813