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

Dataset: The Pile

Neuron 2175 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: 1.4763. Min Range: -1.4763

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1228932 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1102268 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2979. Min Act: -0.0000

Data Index: 1871448 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3433. Min Act: -0.0000

Data Index: 620146 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1196914 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1587. Min Act: -0.0000

Data Index: 998693 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1971535 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1302. Min Act: -0.0000

Data Index: 542519 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.2634. Min Act: -0.0000

Data Index: 939100 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1386620 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1217690 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1417. Min Act: -0.0000

Data Index: 291494 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1854854 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1410215 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1724. Min Act: -0.0000

Data Index: 343082 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1452236 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1041. Min Act: -0.0000

Data Index: 757442 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.0663. Min Act: -0.0000

Data Index: 134530 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 1.4763. Min Range: -1.4763

Max Act: 1.1101. Min Act: -0.0000

Data Index: 38352 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 1.4763. Min Range: -1.4763

Max Act: 0.9665. Min Act: -0.0000

Data Index: 531019 (The Pile)

Max Activating Token Index: 936