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

Dataset: The Pile

Neuron 2504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1562859 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5871. Min Act: -0.0000

Data Index: 469201 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1217956 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6003. Min Act: -0.0000

Data Index: 905046 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6014. Min Act: -0.0000

Data Index: 122503 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1800172 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.7001. Min Act: -0.0001

Data Index: 705697 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5809. Min Act: -0.0000

Data Index: 916923 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1158161 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1635685 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1669800 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1694442 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5846. Min Act: -0.0001

Data Index: 357223 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.4674. Min Act: -0.0001

Data Index: 786997 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.4887. Min Act: -0.0000

Data Index: 104570 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1423037 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1281834 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1130793 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1733289 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1770614 (The Pile)

Max Activating Token Index: 602