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

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

Neuron 5834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.6414. Min Act: -0.0002

Data Index: 654019 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.6367. Min Act: -0.0002

Data Index: 742535 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5888. Min Act: -0.0002

Data Index: 1058976 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5512. Min Act: -0.0002

Data Index: 668614 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5504. Min Act: -0.0002

Data Index: 63456 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5422. Min Act: -0.0002

Data Index: 1224716 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5281. Min Act: -0.0002

Data Index: 936082 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5221. Min Act: -0.0002

Data Index: 415678 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5162. Min Act: -0.0002

Data Index: 421924 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5189. Min Act: -0.0002

Data Index: 84736 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5174. Min Act: -0.0002

Data Index: 3478 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5250. Min Act: -0.0002

Data Index: 1274571 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5152. Min Act: -0.0002

Data Index: 344276 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4940. Min Act: -0.0002

Data Index: 788183 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5041. Min Act: -0.0002

Data Index: 464752 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5118. Min Act: -0.0002

Data Index: 767727 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4980. Min Act: -0.0002

Data Index: 1001998 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.5051. Min Act: -0.0002

Data Index: 892566 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4936. Min Act: -0.0002

Data Index: 69699 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.6414. Min Range: -0.6414

Max Act: 0.4939. Min Act: -0.0002

Data Index: 672520 (C4 (Web Text))

Max Activating Token Index: 467