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

Dataset: The Pile

Neuron 4513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1303503 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1669621 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1891420 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2763. Min Act: -0.0000

Data Index: 743241 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1582715 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2844. Min Act: -0.0000

Data Index: 837835 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1995. Min Act: -0.0000

Data Index: 486860 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0559. Min Act: -0.0000

Data Index: 72523 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1033181 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0460. Min Act: -0.0000

Data Index: 189110 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9992. Min Act: -0.0000

Data Index: 867258 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1419387 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1414142 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9320. Min Act: -0.0000

Data Index: 735073 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1073303 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9418. Min Act: -0.0000

Data Index: 486056 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1472429 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1445936 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8841. Min Act: -0.0000

Data Index: 454402 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1234440 (The Pile)

Max Activating Token Index: 327