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

Dataset: The Pile

Neuron 4621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2734. Min Range: -7.2734

Max Act: 7.2734. Min Act: -0.0000

Data Index: 475863 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 7.2734. Min Range: -7.2734

Max Act: 7.1130. Min Act: -0.0000

Data Index: 55624 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 7.2734. Min Range: -7.2734

Max Act: 7.0088. Min Act: -0.0000

Data Index: 1092879 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.5146. Min Act: -0.0000

Data Index: 969775 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.8248. Min Act: -0.0000

Data Index: 1060768 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.8388. Min Act: -0.0000

Data Index: 128843 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.3729. Min Act: -0.0000

Data Index: 446552 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.2601. Min Act: -0.0000

Data Index: 946530 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.2398. Min Act: -0.0000

Data Index: 1309205 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.3170. Min Act: -0.0000

Data Index: 1770407 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.5433. Min Act: -0.0000

Data Index: 1095534 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.0495. Min Act: -0.0000

Data Index: 893194 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.3870. Min Act: -0.0000

Data Index: 1610268 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 7.2734. Min Range: -7.2734

Max Act: 5.7900. Min Act: -0.0000

Data Index: 341155 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 7.2734. Min Range: -7.2734

Max Act: 5.8694. Min Act: -0.0000

Data Index: 1179305 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.0636. Min Act: -0.0000

Data Index: 967008 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 7.2734. Min Range: -7.2734

Max Act: 5.9554. Min Act: -0.0000

Data Index: 1948935 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 7.2734. Min Range: -7.2734

Max Act: 6.1667. Min Act: -0.0000

Data Index: 694870 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 7.2734. Min Range: -7.2734

Max Act: 5.7529. Min Act: -0.0000

Data Index: 909562 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 7.2734. Min Range: -7.2734

Max Act: 5.7798. Min Act: -0.0000

Data Index: 818329 (The Pile)

Max Activating Token Index: 465