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

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

Neuron 6111 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2808. Min Range: -2.2808

Max Act: 2.2808. Min Act: -0.0000

Data Index: 1356407 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 2.2808. Min Range: -2.2808

Max Act: 2.1697. Min Act: -0.0000

Data Index: 266491 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.2808. Min Range: -2.2808

Max Act: 2.2382. Min Act: -0.0000

Data Index: 906920 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 2.2808. Min Range: -2.2808

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1166843 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.8631. Min Act: -0.0000

Data Index: 133284 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.7779. Min Act: -0.0000

Data Index: 361843 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1630290 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1286991 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.7901. Min Act: -0.0000

Data Index: 1194404 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.6805. Min Act: -0.0000

Data Index: 525781 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1303313 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1522924 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1410794 (Python Code)

Max Activating Token Index: 487

Text #13

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.4507. Min Act: -0.0000

Data Index: 1412377 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1222519 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1121605 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.2777. Min Act: -0.0000

Data Index: 219974 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.2013. Min Act: -0.0000

Data Index: 689379 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.5199. Min Act: -0.0000

Data Index: 356788 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 2.2808. Min Range: -2.2808

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1145634 (C4 (Web Text))

Max Activating Token Index: 416