Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1023390 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.4004. Min Range: -1.4004

Max Act: 1.1716. Min Act: -0.0000

Data Index: 599716 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.8274. Min Act: -0.0000

Data Index: 805198 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7731. Min Act: -0.0000

Data Index: 805213 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7775. Min Act: -0.0000

Data Index: 412968 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7599. Min Act: -0.0000

Data Index: 946902 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1249406 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7314. Min Act: -0.0000

Data Index: 482853 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7478. Min Act: -0.0000

Data Index: 335224 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.6638. Min Act: -0.0000

Data Index: 885217 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1334226 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1070345 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7873. Min Act: -0.0000

Data Index: 955079 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7154. Min Act: -0.0000

Data Index: 240444 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1020656 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7446. Min Act: -0.0000

Data Index: 531112 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.6855. Min Act: -0.0000

Data Index: 190441 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7550. Min Act: -0.0000

Data Index: 819434 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7243. Min Act: -0.0000

Data Index: 856721 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.4004. Min Range: -1.4004

Max Act: 0.7587. Min Act: -0.0000

Data Index: 542136 (C4 (Web Text))

Max Activating Token Index: 962