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

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

Neuron 1774 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1555. Min Act: -0.0001

Data Index: 354735 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2436. Min Act: -0.0001

Data Index: 354580 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1146. Min Act: -0.0001

Data Index: 707685 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1425. Min Act: -0.0000

Data Index: 772912 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0964. Min Act: -0.0001

Data Index: 902323 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1216. Min Act: -0.0001

Data Index: 617671 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1436. Min Act: -0.0001

Data Index: 806705 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0757. Min Act: -0.0001

Data Index: 113706 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1025948 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0935. Min Act: -0.0001

Data Index: 17418 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0740. Min Act: -0.0001

Data Index: 202474 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1031323 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1254. Min Act: -0.0001

Data Index: 381237 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0680. Min Act: -0.0001

Data Index: 406399 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0956. Min Act: -0.0001

Data Index: 946693 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0917. Min Act: -0.0001

Data Index: 905143 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1158. Min Act: -0.0001

Data Index: 211277 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1389. Min Act: -0.0001

Data Index: 67002 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1366. Min Act: -0.0001

Data Index: 999693 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1353686 (C4 (Web Text))

Max Activating Token Index: 996