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

Dataset: The Pile

Neuron 785 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: 1.6683. Min Range: -1.6683

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1740051 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5327. Min Act: -0.0000

Data Index: 1678765 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5684. Min Act: -0.0000

Data Index: 90411 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5838. Min Act: -0.0000

Data Index: 248075 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1801144 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5526. Min Act: -0.0000

Data Index: 1048287 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1247182 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.5407. Min Act: -0.0000

Data Index: 314118 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1537707 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1491654 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1432829 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4263. Min Act: -0.0000

Data Index: 290884 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4182. Min Act: -0.0000

Data Index: 984162 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1788115 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1022024 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1589998 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1192930 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1610871 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3514. Min Act: -0.0000

Data Index: 772459 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 1.6683. Min Range: -1.6683

Max Act: 1.3076. Min Act: -0.0000

Data Index: 389988 (The Pile)

Max Activating Token Index: 504