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

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

Neuron 4092 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.6071. Min Act: -0.0000

Data Index: 877428 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.2899. Min Act: -0.0000

Data Index: 542644 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.7527. Min Act: -0.0001

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.6071. Min Range: -3.6071

Max Act: 3.1598. Min Act: -0.0001

Data Index: 375560 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.7571. Min Act: -0.0000

Data Index: 1300041 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.6003. Min Act: -0.0001

Data Index: 603944 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.6867. Min Act: -0.0000

Data Index: 876139 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.7236. Min Act: -0.0001

Data Index: 1119572 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.3767. Min Act: -0.0000

Data Index: 625786 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.3625. Min Act: -0.0000

Data Index: 564600 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.4837. Min Act: -0.0001

Data Index: 606191 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.4781. Min Act: -0.0001

Data Index: 559669 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.4667. Min Act: -0.0000

Data Index: 450519 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1293061 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.3375. Min Act: -0.0000

Data Index: 465940 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.4620. Min Act: -0.0000

Data Index: 546194 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.4247. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.5454. Min Act: -0.0001

Data Index: 372710 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.2748. Min Act: -0.0000

Data Index: 372929 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 3.6071. Min Range: -3.6071

Max Act: 2.3918. Min Act: -0.0000

Data Index: 101105 (C4 (Web Text))

Max Activating Token Index: 267