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

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

Neuron 200 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: 2.0410. Min Range: -2.0410

Max Act: 1.9719. Min Act: -0.0000

Data Index: 1094146 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.0410. Min Range: -2.0410

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1168865 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.9517. Min Act: -0.0000

Data Index: 843465 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.9522. Min Act: -0.0000

Data Index: 807152 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.9118. Min Act: -0.0000

Data Index: 661139 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.8938. Min Act: -0.0000

Data Index: 468079 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.9479. Min Act: -0.0000

Data Index: 863883 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.8662. Min Act: -0.0000

Data Index: 1347436 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7944. Min Act: -0.0000

Data Index: 1212858 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.8277. Min Act: -0.0000

Data Index: 182930 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7792. Min Act: -0.0000

Data Index: 1352214 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7534. Min Act: -0.0000

Data Index: 489605 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7943. Min Act: -0.0000

Data Index: 1022719 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.6775. Min Act: -0.0000

Data Index: 518611 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.8216. Min Act: -0.0000

Data Index: 354172 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7328. Min Act: -0.0000

Data Index: 784790 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1031014 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1180347 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7167. Min Act: -0.0000

Data Index: 183733 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 2.0410. Min Range: -2.0410

Max Act: 1.7060. Min Act: -0.0000

Data Index: 372522 (C4 (Web Text))

Max Activating Token Index: 951