Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.6162. Min Act: -0.0001

Data Index: 1260212 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5893. Min Act: -0.0001

Data Index: 1130776 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1086362 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5238. Min Act: -0.0001

Data Index: 422717 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5212. Min Act: -0.0001

Data Index: 1160150 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5124. Min Act: -0.0001

Data Index: 780189 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5122. Min Act: -0.0001

Data Index: 674378 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5092. Min Act: -0.0001

Data Index: 376273 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5261. Min Act: -0.0001

Data Index: 880391 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4896. Min Act: -0.0001

Data Index: 278996 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5038. Min Act: -0.0001

Data Index: 191710 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5031. Min Act: -0.0001

Data Index: 516316 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4947. Min Act: -0.0001

Data Index: 46252 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.5065. Min Act: -0.0001

Data Index: 780885 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4898. Min Act: -0.0001

Data Index: 1136832 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4555. Min Act: -0.0001

Data Index: 203395 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4975. Min Act: -0.0001

Data Index: 55866 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4900. Min Act: -0.0001

Data Index: 353559 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4246. Min Act: -0.0001

Data Index: 844323 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.6162. Min Range: -0.6162

Max Act: 0.4734. Min Act: -0.0001

Data Index: 211120 (C4 (Web Text))

Max Activating Token Index: 26