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

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

Neuron 1370 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: 0.1937. Min Range: -0.1937

Max Act: 0.1937. Min Act: -0.0001

Data Index: 956627 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1829. Min Act: -0.0001

Data Index: 361509 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1747. Min Act: -0.0001

Data Index: 842611 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1732. Min Act: -0.0001

Data Index: 88100 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1593. Min Act: -0.0001

Data Index: 646384 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1676. Min Act: -0.0001

Data Index: 460322 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1140946 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1128462 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1478. Min Act: -0.0001

Data Index: 467109 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1314. Min Act: -0.0001

Data Index: 589118 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1146433 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1479. Min Act: -0.0001

Data Index: 318407 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1275194 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1046363 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1273517 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1358. Min Act: -0.0001

Data Index: 952617 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1296. Min Act: -0.0001

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1388. Min Act: -0.0001

Data Index: 983464 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1218142 (C4 (Web Text))

Max Activating Token Index: 533