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

Dataset: The Pile

Neuron 530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1522324 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5695. Min Act: -0.0000

Data Index: 411992 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6685. Min Act: 0.0000

Data Index: 1294807 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1733129 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1397769 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1676328 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1540421 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5225. Min Act: -0.0000

Data Index: 298252 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5061. Min Act: 0.0000

Data Index: 43512 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5045. Min Act: -0.0000

Data Index: 824802 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1927650 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4884. Min Act: -0.0000

Data Index: 610072 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4818. Min Act: -0.0000

Data Index: 933996 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4712. Min Act: -0.0000

Data Index: 770341 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1532969 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1021002 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4324. Min Act: -0.0000

Data Index: 284502 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4229. Min Act: -0.0000

Data Index: 515270 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1504944 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.3052. Min Act: -0.0000

Data Index: 1675006 (The Pile)

Max Activating Token Index: 858