Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3270 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5658. Min Act: -0.0000

Data Index: 832309 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.5120. Min Act: -0.0000

Data Index: 442714 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4951. Min Act: -0.0000

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4557. Min Act: -0.0000

Data Index: 969689 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4675. Min Act: -0.0000

Data Index: 287430 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1114824 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4985. Min Act: -0.0000

Data Index: 219838 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4115. Min Act: -0.0000

Data Index: 304563 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4312. Min Act: -0.0000

Data Index: 112912 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4415. Min Act: -0.0000

Data Index: 494569 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1230676 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4028. Min Act: -0.0000

Data Index: 50708 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4081. Min Act: -0.0000

Data Index: 768458 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4256. Min Act: -0.0000

Data Index: 704611 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4490. Min Act: -0.0000

Data Index: 247575 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4088. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4041. Min Act: -0.0000

Data Index: 274360 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4039. Min Act: -0.0000

Data Index: 659342 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4291. Min Act: -0.0000

Data Index: 397343 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.5658. Min Range: -0.5658

Max Act: 0.4000. Min Act: -0.0000

Data Index: 258806 (C4 (Web Text))

Max Activating Token Index: 255