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

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

Neuron 546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.4075. Min Act: -0.0001

Data Index: 1147108 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1168490 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3372. Min Act: -0.0001

Data Index: 163070 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3701. Min Act: -0.0001

Data Index: 150699 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3403. Min Act: -0.0001

Data Index: 144809 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3159. Min Act: -0.0001

Data Index: 475118 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3504. Min Act: -0.0002

Data Index: 121626 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3270. Min Act: -0.0001

Data Index: 642550 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3300. Min Act: -0.0001

Data Index: 1143249 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3174. Min Act: -0.0001

Data Index: 193106 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2818. Min Act: -0.0001

Data Index: 609359 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1015628 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2798. Min Act: -0.0001

Data Index: 162571 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3280. Min Act: -0.0001

Data Index: 127056 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2856. Min Act: -0.0001

Data Index: 573395 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2930. Min Act: -0.0001

Data Index: 8913 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3188. Min Act: -0.0002

Data Index: 805725 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2866. Min Act: -0.0001

Data Index: 108633 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1285714 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.2818. Min Act: -0.0001

Data Index: 160533 (C4 (Web Text))

Max Activating Token Index: 702