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

Dataset: The Pile

Neuron 4264 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: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1704643 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3497. Min Act: -0.0000

Data Index: 422250 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3728. Min Act: -0.0000

Data Index: 941819 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3488. Min Act: -0.0000

Data Index: 576649 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1560096 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3137. Min Act: -0.0000

Data Index: 411620 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1433312 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3210. Min Act: -0.0000

Data Index: 477669 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2782. Min Act: -0.0000

Data Index: 529044 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2984. Min Act: -0.0000

Data Index: 324346 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3185. Min Act: -0.0000

Data Index: 914696 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3073. Min Act: -0.0000

Data Index: 835438 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3049. Min Act: -0.0000

Data Index: 468102 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1678684 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3249. Min Act: -0.0000

Data Index: 602636 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2946. Min Act: -0.0000

Data Index: 357613 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1604716 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2992. Min Act: -0.0000

Data Index: 237224 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1983590 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1310351 (The Pile)

Max Activating Token Index: 504