Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4573. Min Act: -0.0000

Data Index: 704399 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4276. Min Act: -0.0000

Data Index: 656565 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4079. Min Act: -0.0001

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4097. Min Act: -0.0000

Data Index: 594956 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4078. Min Act: -0.0001

Data Index: 849568 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3710. Min Act: -0.0001

Data Index: 1227949 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3668. Min Act: -0.0000

Data Index: 609206 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3468. Min Act: -0.0001

Data Index: 662272 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3586. Min Act: -0.0000

Data Index: 694896 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3091. Min Act: -0.0000

Data Index: 259854 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2826. Min Act: -0.0001

Data Index: 227615 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3137. Min Act: -0.0000

Data Index: 159724 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3099. Min Act: -0.0000

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2676. Min Act: -0.0000

Data Index: 8793 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2894. Min Act: -0.0000

Data Index: 33521 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2851. Min Act: -0.0000

Data Index: 363207 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2900. Min Act: -0.0000

Data Index: 109699 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2744. Min Act: -0.0000

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1308664 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1252287 (C4 (Web Text))

Max Activating Token Index: 719