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

Dataset: The Pile

Neuron 1227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6670. Min Act: -0.0000

Data Index: 253245 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1880017 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5518. Min Act: -0.0000

Data Index: 613283 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1419336 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1732638 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.6231. Min Act: -0.0000

Data Index: 129115 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1102868 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1956007 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1896544 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3899. Min Act: -0.0000

Data Index: 74957 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1129284 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3864. Min Act: -0.0000

Data Index: 283694 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1026954 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1955295 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3318. Min Act: -0.0000

Data Index: 631203 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1609447 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3009. Min Act: -0.0000

Data Index: 586836 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.4237. Min Act: -0.0000

Data Index: 363006 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1523985 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 1.6670. Min Range: -1.6670

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1950513 (The Pile)

Max Activating Token Index: 254