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

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

Neuron 435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1589705 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1361476 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1410399 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3514. Min Act: -0.0001

Data Index: 1487906 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1477407 (Python Code)

Max Activating Token Index: 702

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1417180 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2045. Min Act: -0.0000

Data Index: 944717 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1357685 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1394968 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1541497 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1256753 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1486546 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1397. Min Act: -0.0000

Data Index: 650339 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1444. Min Act: -0.0000

Data Index: 725170 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1597474 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1489908 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1446713 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1443852 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1441. Min Act: -0.0000

Data Index: 779741 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.1356. Min Act: -0.0000

Data Index: 976620 (C4 (Web Text))

Max Activating Token Index: 367