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

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

Neuron 4136 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1322944 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1609. Min Act: -0.0001

Data Index: 127426 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1577. Min Act: -0.0001

Data Index: 665949 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1555. Min Act: -0.0001

Data Index: 552113 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1347580 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1125862 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1043811 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1461. Min Act: -0.0001

Data Index: 781166 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1373. Min Act: -0.0001

Data Index: 446238 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1190. Min Act: -0.0001

Data Index: 98942 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1391. Min Act: -0.0001

Data Index: 191006 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1149966 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1287. Min Act: -0.0001

Data Index: 216156 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1320. Min Act: -0.0001

Data Index: 434678 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1395. Min Act: -0.0001

Data Index: 951914 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1035176 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1338. Min Act: -0.0001

Data Index: 167336 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1386. Min Act: -0.0001

Data Index: 880788 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1323. Min Act: -0.0001

Data Index: 714730 (C4 (Web Text))

Max Activating Token Index: 386