Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6705. Min Act: -0.0002

Data Index: 817498 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6605. Min Act: -0.0002

Data Index: 525288 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6252. Min Act: -0.0002

Data Index: 308583 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5977. Min Act: -0.0002

Data Index: 1207368 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6022. Min Act: -0.0002

Data Index: 618426 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6236. Min Act: -0.0002

Data Index: 1193236 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5775. Min Act: -0.0002

Data Index: 887520 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5636. Min Act: -0.0002

Data Index: 309090 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5399. Min Act: -0.0002

Data Index: 704183 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5234. Min Act: -0.0002

Data Index: 777279 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5365. Min Act: -0.0002

Data Index: 644115 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5316. Min Act: -0.0002

Data Index: 776301 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4855. Min Act: -0.0002

Data Index: 939694 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5168. Min Act: -0.0002

Data Index: 695910 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5109. Min Act: -0.0002

Data Index: 575883 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5289. Min Act: -0.0002

Data Index: 1025975 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4906. Min Act: -0.0002

Data Index: 1229638 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5054. Min Act: -0.0002

Data Index: 187377 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4834. Min Act: -0.0002

Data Index: 1123804 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4654. Min Act: -0.0002

Data Index: 1125082 (C4 (Web Text))

Max Activating Token Index: 1010