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

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

Neuron 3591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0119. Min Act: -0.0000

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0827. Min Act: -0.0000

Data Index: 872242 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.3893. Min Act: -0.0000

Data Index: 956119 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.1145. Min Act: -0.0000

Data Index: 1238995 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.9959. Min Act: -0.0000

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.0128. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.9818. Min Act: -0.0000

Data Index: 242719 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.9676. Min Act: -0.0000

Data Index: 151244 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.8657. Min Act: -0.0000

Data Index: 1012388 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.8553. Min Act: -0.0000

Data Index: 1349342 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.8673. Min Act: -0.0000

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.9717. Min Act: -0.0000

Data Index: 716924 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.7758. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.7557. Min Act: -0.0000

Data Index: 832015 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.7615. Min Act: -0.0000

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.5972. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.8133. Min Act: -0.0000

Data Index: 1232149 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.6164. Min Act: -0.0000

Data Index: 683871 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.7230. Min Act: -0.0000

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 4.0827. Min Range: -4.0827

Max Act: 2.5339. Min Act: -0.0000

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 780