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

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

Neuron 785 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: 0.7081. Min Range: -0.7081

Max Act: 0.7081. Min Act: -0.0002

Data Index: 895969 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6584. Min Act: -0.0002

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6637. Min Act: -0.0002

Data Index: 661137 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6713. Min Act: -0.0002

Data Index: 1072293 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6498. Min Act: -0.0002

Data Index: 757645 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6495. Min Act: -0.0002

Data Index: 703248 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6521. Min Act: -0.0002

Data Index: 40137 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6261. Min Act: -0.0002

Data Index: 21074 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6296. Min Act: -0.0002

Data Index: 580596 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6257. Min Act: -0.0002

Data Index: 1016237 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6410. Min Act: -0.0002

Data Index: 1269768 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6268. Min Act: -0.0002

Data Index: 657370 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6223. Min Act: -0.0002

Data Index: 695158 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6275. Min Act: -0.0002

Data Index: 1139632 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6213. Min Act: -0.0002

Data Index: 501523 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6115. Min Act: -0.0002

Data Index: 157628 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5949. Min Act: -0.0002

Data Index: 601816 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5959. Min Act: -0.0002

Data Index: 499193 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6025. Min Act: -0.0002

Data Index: 1320217 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6006. Min Act: -0.0002

Data Index: 1343754 (C4 (Web Text))

Max Activating Token Index: 191