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

Dataset: The Pile

Neuron 4706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3969. Min Act: -0.0000

Data Index: 613304 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1722599 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1528663 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4492. Min Act: -0.0000

Data Index: 724817 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4148. Min Act: -0.0000

Data Index: 943853 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1006876 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3715. Min Act: -0.0000

Data Index: 488957 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3932. Min Act: -0.0000

Data Index: 78295 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3656. Min Act: -0.0000

Data Index: 777445 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1457043 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1074386 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3609. Min Act: -0.0001

Data Index: 171994 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1412991 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1509720 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3434. Min Act: -0.0000

Data Index: 382756 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3286. Min Act: -0.0000

Data Index: 352786 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1286696 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.2894. Min Act: -0.0000

Data Index: 499139 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1642577 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1991283 (The Pile)

Max Activating Token Index: 281