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

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

Neuron 534 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: 0.2059. Min Range: -0.2059

Max Act: 0.2059. Min Act: -0.0001

Data Index: 510268 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1815. Min Act: -0.0001

Data Index: 941407 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1667. Min Act: -0.0001

Data Index: 657821 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1559. Min Act: -0.0001

Data Index: 788955 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1030594 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1494. Min Act: -0.0001

Data Index: 128146 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1507. Min Act: -0.0001

Data Index: 128644 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1541. Min Act: -0.0001

Data Index: 144492 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1535. Min Act: -0.0001

Data Index: 841079 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1188149 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1500. Min Act: -0.0001

Data Index: 649335 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1497. Min Act: -0.0001

Data Index: 783754 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1412. Min Act: -0.0001

Data Index: 17925 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1458. Min Act: -0.0001

Data Index: 310868 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1209524 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1407. Min Act: -0.0000

Data Index: 439202 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1450. Min Act: -0.0001

Data Index: 723368 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1393. Min Act: -0.0001

Data Index: 235703 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1081405 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1022046 (C4 (Web Text))

Max Activating Token Index: 736