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

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

Neuron 216 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6190. Min Act: -0.0000

Data Index: 945259 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5439. Min Act: -0.0000

Data Index: 480654 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1537983 (Python Code)

Max Activating Token Index: 509

Text #3

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4884. Min Act: -0.0000

Data Index: 933895 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5035. Min Act: -0.0000

Data Index: 823634 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4754. Min Act: -0.0000

Data Index: 18686 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4726. Min Act: -0.0000

Data Index: 173635 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4821. Min Act: -0.0000

Data Index: 421493 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1278442 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1581578 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4106. Min Act: -0.0000

Data Index: 369944 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4487. Min Act: -0.0001

Data Index: 416097 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1532882 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1569480 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1119591 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4094. Min Act: -0.0000

Data Index: 809133 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.3871. Min Act: -0.0001

Data Index: 1547206 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4211. Min Act: -0.0001

Data Index: 1507668 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1644016 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1373012 (Python Code)

Max Activating Token Index: 89