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

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

Neuron 1636 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: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1646531 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1386819 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1506147 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3311. Min Act: -0.0001

Data Index: 822943 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3403. Min Act: -0.0001

Data Index: 1619108 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3121. Min Act: -0.0001

Data Index: 1426623 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1391254 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3316. Min Act: -0.0001

Data Index: 657431 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1435906 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1488901 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1511535 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1293265 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3096. Min Act: -0.0001

Data Index: 373456 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2988. Min Act: -0.0001

Data Index: 1508283 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1558733 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1525971 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1196356 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1449233 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1621003 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1386302 (Python Code)

Max Activating Token Index: 42