Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.2087. Min Act: -0.0000

Data Index: 335315 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0722. Min Act: -0.0000

Data Index: 781402 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1152913 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9644. Min Act: -0.0000

Data Index: 722353 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.9494. Min Act: -0.0000

Data Index: 838028 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1145925 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.2087. Min Range: -1.2087

Max Act: 1.0013. Min Act: -0.0000

Data Index: 974675 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8468. Min Act: -0.0000

Data Index: 373771 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8180. Min Act: -0.0000

Data Index: 196621 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8350. Min Act: -0.0000

Data Index: 281428 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.8970. Min Act: -0.0000

Data Index: 702133 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7096. Min Act: -0.0000

Data Index: 792470 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7781. Min Act: -0.0000

Data Index: 401112 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7461. Min Act: -0.0000

Data Index: 364811 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.6784. Min Act: -0.0000

Data Index: 102884 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7296. Min Act: -0.0000

Data Index: 278700 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7170. Min Act: -0.0000

Data Index: 172921 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7244. Min Act: -0.0000

Data Index: 408485 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.7249. Min Act: -0.0000

Data Index: 744281 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 1.2087. Min Range: -1.2087

Max Act: 0.6580. Min Act: -0.0000

Data Index: 206908 (C4 (Web Text))

Max Activating Token Index: 241