Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1577 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.3159. Min Act: -0.0001

Data Index: 345891 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1249004 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2962. Min Act: -0.0001

Data Index: 608837 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2947. Min Act: -0.0001

Data Index: 885175 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2594. Min Act: -0.0001

Data Index: 835631 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2401. Min Act: -0.0001

Data Index: 482769 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2480. Min Act: -0.0001

Data Index: 373897 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2736. Min Act: -0.0001

Data Index: 944280 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2498. Min Act: -0.0001

Data Index: 67763 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2605. Min Act: -0.0001

Data Index: 940988 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2677. Min Act: -0.0001

Data Index: 144361 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2427. Min Act: -0.0001

Data Index: 370114 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2720. Min Act: -0.0001

Data Index: 763288 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2551. Min Act: -0.0001

Data Index: 755958 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2447. Min Act: -0.0001

Data Index: 81047 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2599. Min Act: -0.0001

Data Index: 322244 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1013594 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2563. Min Act: -0.0001

Data Index: 5314 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2428. Min Act: -0.0001

Data Index: 138057 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2234. Min Act: -0.0001

Data Index: 348550 (C4 (Web Text))

Max Activating Token Index: 304