Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0000

Data Index: 867245 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1901. Min Act: -0.0000

Data Index: 1197319 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2477. Min Act: -0.0000

Data Index: 688479 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1156770 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1152499 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1470. Min Act: -0.0000

Data Index: 30744 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0904. Min Act: -0.0000

Data Index: 920873 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1023. Min Act: -0.0000

Data Index: 830692 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0741. Min Act: -0.0000

Data Index: 579262 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9151. Min Act: -0.0000

Data Index: 979904 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1046472 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1036409 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1065366 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1232801 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1967533 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1183013 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.8929. Min Act: -0.0000

Data Index: 155772 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.8984. Min Act: -0.0000

Data Index: 744959 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9827. Min Act: -0.0000

Data Index: 811824 (The Pile)

Max Activating Token Index: 924

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 0.9004. Min Act: -0.0000

Data Index: 522478 (The Pile)

Max Activating Token Index: 807