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

Dataset: The Pile

Neuron 2712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.4582. Min Act: -0.0000

Data Index: 475813 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2597. Min Act: -0.0000

Data Index: 870011 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1937182 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2833. Min Act: -0.0000

Data Index: 118748 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1361335 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.4011. Min Act: -0.0000

Data Index: 669680 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1571745 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.4318. Min Act: -0.0000

Data Index: 652415 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.3247. Min Act: -0.0000

Data Index: 553794 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1993686 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1557377 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.2404. Min Act: -0.0000

Data Index: 963607 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1354. Min Act: -0.0000

Data Index: 1201595 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1351. Min Act: -0.0000

Data Index: 242282 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1432. Min Act: -0.0000

Data Index: 510935 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1378. Min Act: -0.0000

Data Index: 767002 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1596264 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1456. Min Act: -0.0000

Data Index: 114717 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.1218. Min Act: -0.0000

Data Index: 182402 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.5208. Min Range: -1.5208

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1955581 (The Pile)

Max Activating Token Index: 624