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

Dataset: The Pile

Neuron 4639 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: 0.4609. Min Range: -0.4609

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1498704 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3563. Min Act: -0.0000

Data Index: 139972 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3682. Min Act: -0.0000

Data Index: 5677 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3438. Min Act: -0.0000

Data Index: 786583 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3326. Min Act: -0.0000

Data Index: 676260 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3323. Min Act: -0.0000

Data Index: 607044 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1104977 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1651906 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3497. Min Act: -0.0000

Data Index: 727855 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3201. Min Act: -0.0000

Data Index: 257188 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3259. Min Act: -0.0000

Data Index: 259523 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3044. Min Act: -0.0000

Data Index: 457045 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3053. Min Act: -0.0000

Data Index: 264527 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1229998 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2946. Min Act: -0.0000

Data Index: 813559 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2999. Min Act: -0.0000

Data Index: 222010 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1253848 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2943. Min Act: -0.0000

Data Index: 396156 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1573145 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2983. Min Act: -0.0000

Data Index: 222724 (The Pile)

Max Activating Token Index: 954