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

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

Neuron 645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9689. Min Act: -0.0000

Data Index: 446956 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1062113 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1143741 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9127. Min Act: -0.0000

Data Index: 772354 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.9049. Min Act: -0.0000

Data Index: 742666 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8994. Min Act: -0.0000

Data Index: 505298 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8399. Min Act: -0.0000

Data Index: 897967 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8932. Min Act: -0.0000

Data Index: 664019 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8602. Min Act: -0.0000

Data Index: 356607 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8375. Min Act: -0.0000

Data Index: 799593 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8369. Min Act: -0.0000

Data Index: 472109 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8162. Min Act: -0.0000

Data Index: 183755 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1246004 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8070. Min Act: -0.0000

Data Index: 293977 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1190267 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1223985 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8421. Min Act: -0.0000

Data Index: 211609 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1309952 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.8165. Min Act: -0.0000

Data Index: 125368 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.9815. Min Range: -0.9815

Max Act: 0.7667. Min Act: -0.0000

Data Index: 423782 (C4 (Web Text))

Max Activating Token Index: 653