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

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

Neuron 2067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7103. Min Range: -5.7103

Max Act: 5.7103. Min Act: -0.0000

Data Index: 625362 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 5.7103. Min Range: -5.7103

Max Act: 5.5593. Min Act: -0.0000

Data Index: 354171 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 5.7103. Min Range: -5.7103

Max Act: 5.1862. Min Act: -0.0000

Data Index: 602455 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 5.7103. Min Range: -5.7103

Max Act: 4.3296. Min Act: -0.0000

Data Index: 1158308 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.9890. Min Act: -0.0000

Data Index: 68698 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.5115. Min Act: -0.0000

Data Index: 1243378 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.6726. Min Act: -0.0000

Data Index: 1126577 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.7679. Min Act: -0.0000

Data Index: 1001442 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.3529. Min Act: -0.0000

Data Index: 246178 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.3222. Min Act: -0.0000

Data Index: 1067768 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.2365. Min Act: -0.0000

Data Index: 1335752 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.1757. Min Act: -0.0000

Data Index: 745490 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.1241. Min Act: -0.0000

Data Index: 566280 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0970. Min Act: -0.0000

Data Index: 1171542 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0547. Min Act: -0.0000

Data Index: 882470 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 5.7103. Min Range: -5.7103

Max Act: 2.9062. Min Act: -0.0000

Data Index: 47137 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0390. Min Act: -0.0000

Data Index: 903344 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0115. Min Act: -0.0000

Data Index: 1094204 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0180. Min Act: -0.0000

Data Index: 422815 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 5.7103. Min Range: -5.7103

Max Act: 3.0087. Min Act: -0.0000

Data Index: 432836 (C4 (Web Text))

Max Activating Token Index: 836