Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1581222 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1527419 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1393804 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1372033 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1586833 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2046. Min Act: -0.0000

Data Index: 883870 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1369624 (Python Code)

Max Activating Token Index: 851

Text #7

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1453887 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2066. Min Act: -0.0000

Data Index: 930567 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1559533 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1572379 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1406546 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1488278 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1122491 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1620201 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1400041 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1484583 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1392194 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1388051 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1189299 (C4 (Web Text))

Max Activating Token Index: 804