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

Dataset: The Pile

Neuron 3981 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: 0.3081. Min Range: -0.3081

Max Act: 0.2933. Min Act: -0.0000

Data Index: 774024 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 498277 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2800. Min Act: -0.0000

Data Index: 793141 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1846046 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2756. Min Act: -0.0000

Data Index: 883722 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1320589 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2957. Min Act: -0.0000

Data Index: 903330 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2473. Min Act: -0.0000

Data Index: 563572 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2634. Min Act: -0.0000

Data Index: 568575 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2321. Min Act: -0.0000

Data Index: 751285 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2513. Min Act: -0.0000

Data Index: 842796 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2390. Min Act: -0.0000

Data Index: 12986 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1989306 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2371. Min Act: -0.0000

Data Index: 623199 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2516. Min Act: -0.0000

Data Index: 431198 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1579016 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2399. Min Act: -0.0000

Data Index: 899646 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2376. Min Act: -0.0000

Data Index: 407579 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1602837 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2563. Min Act: -0.0000

Data Index: 924275 (The Pile)

Max Activating Token Index: 251