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

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

Neuron 151 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0120. Min Range: -6.0120

Max Act: 6.0120. Min Act: -0.0000

Data Index: 1089350 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 6.0120. Min Range: -6.0120

Max Act: 5.8031. Min Act: -0.0000

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 6.0120. Min Range: -6.0120

Max Act: 5.3235. Min Act: -0.0000

Data Index: 56633 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 6.0120. Min Range: -6.0120

Max Act: 5.0513. Min Act: -0.0000

Data Index: 912811 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.9540. Min Act: -0.0000

Data Index: 205521 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.7057. Min Act: -0.0000

Data Index: 277904 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.9866. Min Act: -0.0000

Data Index: 1006632 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.8319. Min Act: -0.0000

Data Index: 75011 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.6826. Min Act: -0.0000

Data Index: 553316 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.7580. Min Act: -0.0000

Data Index: 961853 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.5677. Min Act: -0.0000

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.5061. Min Act: -0.0000

Data Index: 724536 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.2151. Min Act: -0.0000

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.1771. Min Act: -0.0000

Data Index: 399155 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.6650. Min Act: -0.0000

Data Index: 559231 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.5288. Min Act: -0.0000

Data Index: 1116044 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.4809. Min Act: -0.0000

Data Index: 207461 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 6.0120. Min Range: -6.0120

Max Act: 3.9475. Min Act: -0.0000

Data Index: 1359313 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.3057. Min Act: -0.0000

Data Index: 984318 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 6.0120. Min Range: -6.0120

Max Act: 4.1166. Min Act: -0.0000

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 441