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

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

Neuron 3739 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: 2.3108. Min Range: -2.3108

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1386792 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.3108. Min Act: -0.0000

Data Index: 1584751 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1958. Min Act: -0.0000

Data Index: 1487463 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.2177. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1950. Min Act: -0.0000

Data Index: 449626 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1847. Min Act: -0.0000

Data Index: 1599063 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1149. Min Act: -0.0000

Data Index: 451328 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1695. Min Act: -0.0000

Data Index: 1566632 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1366831 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1438. Min Act: -0.0000

Data Index: 1630198 (Python Code)

Max Activating Token Index: 344

Text #10

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.0307. Min Act: -0.0000

Data Index: 386075 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.0654. Min Act: -0.0000

Data Index: 1590415 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1142. Min Act: -0.0000

Data Index: 1475169 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1090. Min Act: -0.0000

Data Index: 1427234 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1653794 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1643430 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1634573 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1127. Min Act: -0.0000

Data Index: 1470270 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1074. Min Act: -0.0000

Data Index: 1611592 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 2.3108. Min Range: -2.3108

Max Act: 2.1095. Min Act: -0.0000

Data Index: 1492574 (Python Code)

Max Activating Token Index: 67