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

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

Neuron 1208 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: 0.6054. Min Range: -0.6054

Max Act: 0.6054. Min Act: -0.0002

Data Index: 174194 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5865. Min Act: -0.0002

Data Index: 309913 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5940. Min Act: -0.0003

Data Index: 1117402 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5935. Min Act: -0.0002

Data Index: 909516 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5904. Min Act: -0.0002

Data Index: 235095 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5692. Min Act: -0.0002

Data Index: 59343 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5614. Min Act: -0.0002

Data Index: 873068 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5437. Min Act: -0.0002

Data Index: 1030512 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5401. Min Act: -0.0002

Data Index: 131274 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5423. Min Act: -0.0002

Data Index: 9574 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5147. Min Act: -0.0002

Data Index: 281733 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5363. Min Act: -0.0002

Data Index: 594513 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5185. Min Act: -0.0003

Data Index: 723050 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5246. Min Act: -0.0002

Data Index: 1326715 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5257. Min Act: -0.0002

Data Index: 651516 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5214. Min Act: -0.0003

Data Index: 554529 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5068. Min Act: -0.0002

Data Index: 384372 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5024. Min Act: -0.0002

Data Index: 225090 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5115. Min Act: -0.0002

Data Index: 804879 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5045. Min Act: -0.0002

Data Index: 997254 (C4 (Web Text))

Max Activating Token Index: 425