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

Dataset: The Pile

Neuron 746 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1863754 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7854. Min Act: -0.0000

Data Index: 129289 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7605. Min Act: 0.0000

Data Index: 46268 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7284. Min Act: -0.0000

Data Index: 191093 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1505936 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1039289 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6754. Min Act: -0.0000

Data Index: 523215 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6462. Min Act: -0.0000

Data Index: 923090 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1087056 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5956. Min Act: -0.0000

Data Index: 685911 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5544. Min Act: -0.0000

Data Index: 251359 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1110899 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1331641 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1574266 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1589734 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1101927 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1204257 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1148798 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5364. Min Act: -0.0000

Data Index: 985366 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1712023 (The Pile)

Max Activating Token Index: 182