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

Dataset: The Pile

Neuron 797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1301940 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4775. Min Act: -0.0000

Data Index: 18307 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1755792 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3408. Min Act: -0.0000

Data Index: 392767 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1091548 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1048283 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1246127 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3129. Min Act: -0.0000

Data Index: 265223 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1696574 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1403280 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2877. Min Act: -0.0000

Data Index: 554964 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2978. Min Act: -0.0000

Data Index: 643351 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2713. Min Act: -0.0000

Data Index: 580900 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1529720 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2832. Min Act: -0.0000

Data Index: 502642 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1580425 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3092. Min Act: -0.0000

Data Index: 770451 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2807. Min Act: -0.0000

Data Index: 140758 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2700. Min Act: -0.0000

Data Index: 437568 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.2764. Min Act: -0.0000

Data Index: 85398 (The Pile)

Max Activating Token Index: 346