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

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

Neuron 773 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: 0.2083. Min Range: -0.2083

Max Act: 0.2083. Min Act: -0.0001

Data Index: 161873 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1939. Min Act: -0.0000

Data Index: 701341 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1079818 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1665. Min Act: -0.0001

Data Index: 998224 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1443. Min Act: -0.0000

Data Index: 180061 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1489. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1029476 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1471. Min Act: -0.0001

Data Index: 411420 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1517. Min Act: -0.0000

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1328931 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1443. Min Act: -0.0001

Data Index: 757019 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1331862 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1013445 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1391. Min Act: -0.0000

Data Index: 524301 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1398. Min Act: -0.0001

Data Index: 223786 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1032369 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1343. Min Act: -0.0001

Data Index: 513368 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1415. Min Act: -0.0001

Data Index: 411766 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1374. Min Act: -0.0000

Data Index: 715156 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1288. Min Act: -0.0000

Data Index: 567985 (C4 (Web Text))

Max Activating Token Index: 374