Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2731. Min Act: -0.0001

Data Index: 258330 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2541. Min Act: -0.0001

Data Index: 1314042 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2106. Min Act: -0.0001

Data Index: 211855 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2113. Min Act: -0.0001

Data Index: 255284 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2390. Min Act: -0.0001

Data Index: 1231204 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2238. Min Act: -0.0001

Data Index: 819912 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1182914 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2071. Min Act: -0.0001

Data Index: 920293 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2119. Min Act: -0.0001

Data Index: 193308 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1945. Min Act: -0.0001

Data Index: 715374 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2097. Min Act: -0.0001

Data Index: 557702 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.2091. Min Act: -0.0001

Data Index: 192995 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1174799 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1968. Min Act: -0.0001

Data Index: 529828 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1803. Min Act: -0.0001

Data Index: 421899 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1878. Min Act: -0.0001

Data Index: 150257 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1728. Min Act: -0.0001

Data Index: 479347 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1702. Min Act: -0.0001

Data Index: 944787 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1204977 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2731. Min Range: -0.2731

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1204171 (C4 (Web Text))

Max Activating Token Index: 229