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

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

Neuron 2005 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2941. Min Act: 0.0000

Data Index: 402918 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0870. Min Act: -0.0000

Data Index: 442744 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0590. Min Act: -0.0000

Data Index: 837038 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1151446 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.9695. Min Act: -0.0000

Data Index: 445711 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.8919. Min Act: -0.0000

Data Index: 239730 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7042. Min Act: -0.0000

Data Index: 497627 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1095434 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7749. Min Act: -0.0000

Data Index: 480153 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1043107 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7430. Min Act: -0.0000

Data Index: 502145 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7090. Min Act: -0.0000

Data Index: 175128 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7050. Min Act: -0.0000

Data Index: 299317 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1035124 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7738. Min Act: -0.0000

Data Index: 66968 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.6658. Min Act: -0.0000

Data Index: 269219 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.6631. Min Act: -0.0000

Data Index: 787502 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.7117. Min Act: -0.0000

Data Index: 712084 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.6462. Min Act: -0.0000

Data Index: 348096 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 1.2941. Min Range: -1.2941

Max Act: 0.6745. Min Act: -0.0000

Data Index: 823832 (C4 (Web Text))

Max Activating Token Index: 482