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

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

Neuron 5200 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: 1.2001. Min Range: -1.2001

Max Act: 1.2001. Min Act: -0.0000

Data Index: 139804 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1076352 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1233777 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.0697. Min Act: 0.0000

Data Index: 537203 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.2001. Min Range: -1.2001

Max Act: 1.0318. Min Act: -0.0000

Data Index: 40814 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8843. Min Act: -0.0000

Data Index: 254568 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.9417. Min Act: -0.0000

Data Index: 444725 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8974. Min Act: 0.0000

Data Index: 379108 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8609. Min Act: -0.0000

Data Index: 479668 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8827. Min Act: -0.0000

Data Index: 534324 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8779. Min Act: -0.0000

Data Index: 838243 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1221551 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8096. Min Act: 0.0000

Data Index: 839947 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1255185 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1021494 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1230600 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8321. Min Act: -0.0000

Data Index: 391827 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8052. Min Act: -0.0000

Data Index: 100658 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8244. Min Act: -0.0000

Data Index: 509798 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.2001. Min Range: -1.2001

Max Act: 0.8496. Min Act: -0.0000

Data Index: 510803 (C4 (Web Text))

Max Activating Token Index: 764