Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6161. Min Act: -0.0004

Data Index: 382138 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5426. Min Act: -0.0004

Data Index: 823805 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5057. Min Act: -0.0004

Data Index: 677956 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5383. Min Act: -0.0004

Data Index: 266846 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5299. Min Act: -0.0004

Data Index: 148239 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5637. Min Act: -0.0004

Data Index: 277600 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5424. Min Act: -0.0004

Data Index: 43927 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5626. Min Act: -0.0004

Data Index: 836233 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5750. Min Act: -0.0004

Data Index: 1258200 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5731. Min Act: -0.0004

Data Index: 948364 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5345. Min Act: -0.0004

Data Index: 875415 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5144. Min Act: -0.0004

Data Index: 866049 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5343. Min Act: -0.0004

Data Index: 946746 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5172. Min Act: -0.0004

Data Index: 1295350 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5134. Min Act: -0.0004

Data Index: 1173379 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5263. Min Act: -0.0004

Data Index: 224950 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5584. Min Act: -0.0004

Data Index: 198772 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5428. Min Act: -0.0004

Data Index: 839254 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5592. Min Act: -0.0004

Data Index: 1314372 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5419. Min Act: -0.0004

Data Index: 859872 (C4 (Web Text))

Max Activating Token Index: 16