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

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

Neuron 2278 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: 0.5436. Min Range: -0.5436

Max Act: 0.5436. Min Act: -0.0001

Data Index: 1636822 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.5130. Min Act: -0.0000

Data Index: 345271 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4497. Min Act: -0.0001

Data Index: 1500412 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1629551 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1515562 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4443. Min Act: 0.0000

Data Index: 1046221 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4212. Min Act: -0.0001

Data Index: 1650363 (Python Code)

Max Activating Token Index: 223

Text #7

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1410784 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4147. Min Act: -0.0001

Data Index: 1454774 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1572155 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1576919 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1502260 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4049. Min Act: -0.0001

Data Index: 1399417 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1530363 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.3894. Min Act: -0.0001

Data Index: 1551754 (Python Code)

Max Activating Token Index: 547

Text #15

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.3795. Min Act: -0.0000

Data Index: 744210 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1444874 (Python Code)

Max Activating Token Index: 690

Text #17

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.3909. Min Act: -0.0001

Data Index: 618991 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1475232 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 0.5436. Min Range: -0.5436

Max Act: 0.4014. Min Act: -0.0001

Data Index: 1526498 (Python Code)

Max Activating Token Index: 123