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

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

Neuron 4912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.6315. Min Act: -0.0001

Data Index: 112341 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.4091. Min Act: -0.0001

Data Index: 1293336 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.2162. Min Act: -0.0001

Data Index: 977916 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.1673. Min Act: -0.0001

Data Index: 264603 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.2333. Min Act: -0.0001

Data Index: 298264 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.0111. Min Act: -0.0001

Data Index: 196772 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.0216. Min Act: -0.0001

Data Index: 205913 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.1051. Min Act: -0.0001

Data Index: 824803 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.8585. Min Act: -0.0001

Data Index: 437396 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.8442. Min Act: -0.0001

Data Index: 278405 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.9704. Min Act: -0.0001

Data Index: 757707 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.6315. Min Range: -3.6315

Max Act: 3.0107. Min Act: -0.0001

Data Index: 800396 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.8529. Min Act: -0.0001

Data Index: 1012079 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.7280. Min Act: -0.0001

Data Index: 670428 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.8253. Min Act: -0.0001

Data Index: 501778 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.7641. Min Act: -0.0001

Data Index: 118784 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.7690. Min Act: -0.0001

Data Index: 1053517 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.8996. Min Act: -0.0001

Data Index: 1191403 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.7466. Min Act: -0.0001

Data Index: 1213336 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.6315. Min Range: -3.6315

Max Act: 2.5936. Min Act: -0.0001

Data Index: 964162 (C4 (Web Text))

Max Activating Token Index: 596