Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1245 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0046. Min Range: -4.0046

Max Act: 4.0046. Min Act: -0.0000

Data Index: 532011 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.8427. Min Act: -0.0000

Data Index: 1353360 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.6116. Min Act: -0.0000

Data Index: 759439 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.4152. Min Act: -0.0000

Data Index: 501908 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.2951. Min Act: -0.0000

Data Index: 1270380 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.3692. Min Act: -0.0000

Data Index: 1076 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.3608. Min Act: -0.0000

Data Index: 488007 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.1902. Min Act: -0.0000

Data Index: 40446 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.3431. Min Act: -0.0000

Data Index: 426534 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.3278. Min Act: -0.0000

Data Index: 244333 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.1230. Min Act: -0.0000

Data Index: 870911 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.4305. Min Act: -0.0000

Data Index: 107545 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.2139. Min Act: -0.0000

Data Index: 343663 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.2283. Min Act: -0.0000

Data Index: 394978 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.3058. Min Act: -0.0000

Data Index: 468796 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.1227. Min Act: -0.0000

Data Index: 860792 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.1443. Min Act: -0.0000

Data Index: 704475 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.2759. Min Act: -0.0000

Data Index: 1312689 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.0703. Min Act: -0.0000

Data Index: 210286 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.0046. Min Range: -4.0046

Max Act: 3.0485. Min Act: -0.0000

Data Index: 1131577 (C4 (Web Text))

Max Activating Token Index: 602