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

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

Neuron 4264 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: 1.8057. Min Range: -1.8057

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1338910 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.6371. Min Act: -0.0000

Data Index: 242116 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1249278 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5682. Min Act: -0.0000

Data Index: 118578 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1107267 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4468. Min Act: -0.0000

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5686. Min Act: -0.0000

Data Index: 866397 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3849. Min Act: -0.0000

Data Index: 804705 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3542. Min Act: -0.0000

Data Index: 978153 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1088402 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2292. Min Act: -0.0000

Data Index: 919539 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2770. Min Act: -0.0000

Data Index: 502358 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0957. Min Act: -0.0000

Data Index: 604784 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2162. Min Act: -0.0000

Data Index: 652815 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1117262 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1071326 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1532. Min Act: -0.0000

Data Index: 14711 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1305341 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1025673 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 246