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

Dataset: The Pile

Neuron 2664 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: 4.2519. Min Range: -4.2519

Max Act: 4.2519. Min Act: -0.0000

Data Index: 951172 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 4.2519. Min Range: -4.2519

Max Act: 4.0858. Min Act: -0.0000

Data Index: 142778 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.9463. Min Act: -0.0000

Data Index: 964352 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.5886. Min Act: -0.0000

Data Index: 1669478 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3599. Min Act: -0.0000

Data Index: 1585188 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.4533. Min Act: -0.0000

Data Index: 207717 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.2774. Min Act: -0.0000

Data Index: 737677 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.0311. Min Act: -0.0000

Data Index: 555707 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.2478. Min Act: -0.0000

Data Index: 1874507 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.1412. Min Act: -0.0000

Data Index: 1538861 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.1193. Min Act: -0.0000

Data Index: 1561111 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.0984. Min Act: -0.0000

Data Index: 411727 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.0887. Min Act: -0.0000

Data Index: 1645340 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 4.2519. Min Range: -4.2519

Max Act: 2.9068. Min Act: -0.0000

Data Index: 1139369 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 4.2519. Min Range: -4.2519

Max Act: 2.8952. Min Act: -0.0000

Data Index: 1037653 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.0565. Min Act: -0.0000

Data Index: 587357 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 4.2519. Min Range: -4.2519

Max Act: 2.9253. Min Act: -0.0000

Data Index: 1742095 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 4.2519. Min Range: -4.2519

Max Act: 2.8393. Min Act: -0.0000

Data Index: 307314 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 4.2519. Min Range: -4.2519

Max Act: 2.8281. Min Act: -0.0000

Data Index: 1213390 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.0842. Min Act: -0.0000

Data Index: 1373504 (The Pile)

Max Activating Token Index: 997