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

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

Neuron 2538 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1201403 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2456. Min Act: -0.0000

Data Index: 476735 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2275. Min Act: -0.0000

Data Index: 548816 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2230. Min Act: -0.0001

Data Index: 884156 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1118805 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2176. Min Act: -0.0000

Data Index: 808596 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2156. Min Act: -0.0000

Data Index: 349362 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2034. Min Act: -0.0000

Data Index: 890783 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2185. Min Act: -0.0001

Data Index: 585202 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2100. Min Act: -0.0000

Data Index: 242368 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2093. Min Act: -0.0000

Data Index: 904549 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2155. Min Act: -0.0000

Data Index: 915797 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1257624 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2112. Min Act: -0.0000

Data Index: 400659 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2041. Min Act: -0.0000

Data Index: 475539 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1965. Min Act: -0.0000

Data Index: 263791 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2005. Min Act: -0.0001

Data Index: 452667 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1989. Min Act: -0.0001

Data Index: 901872 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1985. Min Act: -0.0000

Data Index: 262026 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1970. Min Act: -0.0000

Data Index: 77882 (C4 (Web Text))

Max Activating Token Index: 962