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

Dataset: The Pile

Neuron 3571 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.7465. Min Act: -0.0000

Data Index: 281090 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.0457. Min Act: -0.0000

Data Index: 1345580 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.0389. Min Act: -0.0000

Data Index: 883587 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.1947. Min Act: -0.0000

Data Index: 293118 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.9288. Min Act: -0.0000

Data Index: 732736 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.8439. Min Act: -0.0000

Data Index: 979276 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1476612 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.8339. Min Act: -0.0000

Data Index: 506351 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.7647. Min Act: -0.0000

Data Index: 1607622 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1636976 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1167477 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1593830 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.7837. Min Act: -0.0000

Data Index: 160550 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.5711. Min Act: -0.0000

Data Index: 298743 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1820839 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.4313. Min Act: -0.0000

Data Index: 969904 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.5799. Min Act: -0.0000

Data Index: 176135 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.5844. Min Act: -0.0000

Data Index: 916717 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1294051 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 3.7465. Min Range: -3.7465

Max Act: 1.4179. Min Act: -0.0000

Data Index: 808104 (The Pile)

Max Activating Token Index: 255