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

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

Neuron 1255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1286198 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3785. Min Act: -0.0001

Data Index: 117300 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3544. Min Act: -0.0001

Data Index: 1353857 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3438. Min Act: -0.0001

Data Index: 411995 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3348. Min Act: -0.0001

Data Index: 495603 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2962. Min Act: -0.0001

Data Index: 651129 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1039479 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3063. Min Act: -0.0001

Data Index: 935368 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2828. Min Act: -0.0001

Data Index: 475611 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2918. Min Act: -0.0001

Data Index: 894171 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2592. Min Act: -0.0001

Data Index: 475722 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2726. Min Act: -0.0001

Data Index: 666390 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2786. Min Act: -0.0001

Data Index: 948464 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1089433 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2538. Min Act: -0.0001

Data Index: 977871 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2663. Min Act: -0.0001

Data Index: 974688 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1270907 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2494. Min Act: -0.0001

Data Index: 918446 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1294231 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2424. Min Act: -0.0001

Data Index: 439078 (C4 (Web Text))

Max Activating Token Index: 603