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

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

Neuron 1327 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: 2.3299. Min Range: -2.3299

Max Act: 1.9272. Min Act: -0.0000

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 2.3299. Min Range: -2.3299

Max Act: 2.3299. Min Act: -0.0000

Data Index: 955837 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.8154. Min Act: -0.0000

Data Index: 8419 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.9115. Min Act: -0.0000

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.7945. Min Act: -0.0000

Data Index: 840618 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.6239. Min Act: -0.0000

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1043415 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.6188. Min Act: -0.0000

Data Index: 662504 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.6080. Min Act: -0.0000

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.6072. Min Act: -0.0000

Data Index: 18578 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.5307. Min Act: -0.0000

Data Index: 916219 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.5525. Min Act: -0.0000

Data Index: 553517 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.3784. Min Act: -0.0000

Data Index: 375777 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1072526 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.4180. Min Act: -0.0000

Data Index: 617795 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.3727. Min Act: -0.0000

Data Index: 624807 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.2940. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1178813 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 2.3299. Min Range: -2.3299

Max Act: 1.3006. Min Act: -0.0000

Data Index: 520134 (C4 (Web Text))

Max Activating Token Index: 169