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

Dataset: The Pile

Neuron 1483 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: 1.4389. Min Range: -1.4389

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1768035 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2261. Min Act: -0.0000

Data Index: 1137408 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2982. Min Act: -0.0000

Data Index: 700177 (The Pile)

Max Activating Token Index: 230

Text #3

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2683. Min Act: -0.0000

Data Index: 138161 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2393. Min Act: -0.0000

Data Index: 256186 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1606. Min Act: -0.0000

Data Index: 578479 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1661. Min Act: -0.0000

Data Index: 956828 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1273602 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2096. Min Act: -0.0000

Data Index: 620291 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1734608 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1985025 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.2307. Min Act: -0.0000

Data Index: 409374 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0865. Min Act: -0.0000

Data Index: 160964 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0484. Min Act: -0.0000

Data Index: 628424 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1681094 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1412. Min Act: -0.0000

Data Index: 495670 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0964. Min Act: -0.0000

Data Index: 785650 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.1255. Min Act: -0.0000

Data Index: 378284 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0576. Min Act: -0.0000

Data Index: 559865 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 1.4389. Min Range: -1.4389

Max Act: 1.0525. Min Act: -0.0000

Data Index: 599317 (The Pile)

Max Activating Token Index: 482