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

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

Neuron 4457 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5020. Min Range: -3.5020

Max Act: 3.5020. Min Act: -0.0000

Data Index: 376192 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 3.5020. Min Range: -3.5020

Max Act: 3.3206. Min Act: -0.0000

Data Index: 372853 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.5020. Min Range: -3.5020

Max Act: 3.4186. Min Act: -0.0000

Data Index: 535750 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.5020. Min Range: -3.5020

Max Act: 3.1182. Min Act: -0.0000

Data Index: 252819 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.9441. Min Act: -0.0000

Data Index: 841308 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.9719. Min Act: -0.0000

Data Index: 948357 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.9305. Min Act: -0.0000

Data Index: 943756 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.9153. Min Act: -0.0000

Data Index: 178741 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8923. Min Act: -0.0000

Data Index: 1276928 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8814. Min Act: -0.0000

Data Index: 987995 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8830. Min Act: -0.0000

Data Index: 180789 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8169. Min Act: -0.0000

Data Index: 1259204 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8161. Min Act: -0.0000

Data Index: 961001 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.6734. Min Act: -0.0000

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.8110. Min Act: -0.0000

Data Index: 731775 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.7956. Min Act: -0.0000

Data Index: 605791 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.7794. Min Act: -0.0000

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.9275. Min Act: -0.0000

Data Index: 24912 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.7805. Min Act: -0.0000

Data Index: 579623 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 3.5020. Min Range: -3.5020

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1012494 (C4 (Web Text))

Max Activating Token Index: 900