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

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

Neuron 546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1150341 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0001

Data Index: 668917 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1223383 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0303. Min Act: -0.0001

Data Index: 523767 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0311. Min Act: -0.0001

Data Index: 806639 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0270. Min Act: -0.0001

Data Index: 55804 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1151413 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0282. Min Act: -0.0001

Data Index: 266046 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0277. Min Act: -0.0001

Data Index: 320460 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1274160 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0254. Min Act: -0.0001

Data Index: 11820 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0214. Min Act: -0.0001

Data Index: 901738 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0234. Min Act: -0.0001

Data Index: 275149 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0242. Min Act: -0.0001

Data Index: 312336 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0242. Min Act: -0.0001

Data Index: 133258 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1332889 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0227. Min Act: -0.0001

Data Index: 569010 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0245. Min Act: -0.0001

Data Index: 669491 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0236. Min Act: -0.0001

Data Index: 617896 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0231. Min Act: -0.0001

Data Index: 581956 (C4 (Web Text))

Max Activating Token Index: 8