Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.7233. Min Act: 0.0000

Data Index: 88873 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 5.1807. Min Range: -5.1807

Max Act: 5.1807. Min Act: -0.0000

Data Index: 250720 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.4807. Min Act: -0.0000

Data Index: 1463049 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.5121. Min Act: -0.0000

Data Index: 577558 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.3257. Min Act: -0.0000

Data Index: 498845 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.0696. Min Act: -0.0000

Data Index: 93165 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 5.1807. Min Range: -5.1807

Max Act: 4.2134. Min Act: -0.0000

Data Index: 256584 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.6860. Min Act: -0.0000

Data Index: 1981838 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.7777. Min Act: -0.0000

Data Index: 116175 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.6095. Min Act: -0.0000

Data Index: 337314 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2870. Min Act: -0.0000

Data Index: 1744940 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.5029. Min Act: -0.0000

Data Index: 1682431 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.4384. Min Act: -0.0000

Data Index: 1845287 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2644. Min Act: -0.0000

Data Index: 1230952 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.5555. Min Act: -0.0000

Data Index: 439139 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2736. Min Act: 0.0000

Data Index: 1300117 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2584. Min Act: -0.0000

Data Index: 1344568 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2619. Min Act: -0.0000

Data Index: 458617 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 5.1807. Min Range: -5.1807

Max Act: 2.9333. Min Act: -0.0000

Data Index: 816319 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 5.1807. Min Range: -5.1807

Max Act: 3.2005. Min Act: -0.0000

Data Index: 1139412 (The Pile)

Max Activating Token Index: 226