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

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

Neuron 4036 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: 2.1676. Min Range: -2.1676

Max Act: 2.1676. Min Act: -0.0000

Data Index: 709643 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8945. Min Act: -0.0000

Data Index: 8854 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 2.1676. Min Range: -2.1676

Max Act: 2.0205. Min Act: -0.0000

Data Index: 401758 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.1676. Min Range: -2.1676

Max Act: 2.0304. Min Act: -0.0000

Data Index: 1075936 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8805. Min Act: -0.0000

Data Index: 541161 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8618. Min Act: -0.0000

Data Index: 268136 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8214. Min Act: -0.0000

Data Index: 221071 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8050. Min Act: -0.0000

Data Index: 253422 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.6726. Min Act: -0.0000

Data Index: 1271290 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7772. Min Act: -0.0000

Data Index: 415027 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7688. Min Act: -0.0000

Data Index: 342752 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7580. Min Act: -0.0000

Data Index: 415649 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7978. Min Act: -0.0000

Data Index: 186853 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7678. Min Act: -0.0000

Data Index: 438289 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7139. Min Act: -0.0000

Data Index: 1151950 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.6862. Min Act: -0.0000

Data Index: 745318 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.8358. Min Act: -0.0000

Data Index: 513818 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1065780 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7496. Min Act: -0.0000

Data Index: 213624 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 2.1676. Min Range: -2.1676

Max Act: 1.7085. Min Act: -0.0000

Data Index: 675133 (C4 (Web Text))

Max Activating Token Index: 307