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

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

Neuron 1587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1283931 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.4532. Min Act: -0.0000

Data Index: 579810 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1626074 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.4977. Min Act: -0.0000

Data Index: 929314 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.3983. Min Act: -0.0000

Data Index: 1347385 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.4669. Min Act: -0.0000

Data Index: 259143 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1259200 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1109219 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.3089. Min Act: -0.0000

Data Index: 568477 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.3231. Min Act: -0.0000

Data Index: 302103 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1491280 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1277330 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2000. Min Act: -0.0000

Data Index: 497556 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1917. Min Act: -0.0000

Data Index: 17093 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0851. Min Act: -0.0000

Data Index: 415430 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1162. Min Act: -0.0000

Data Index: 483986 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2219. Min Act: -0.0000

Data Index: 428976 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1563462 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1462. Min Act: -0.0000

Data Index: 526549 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0303. Min Act: -0.0000

Data Index: 978399 (C4 (Web Text))

Max Activating Token Index: 194