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

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

Neuron 712 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: 2.2960. Min Range: -2.2960

Max Act: 2.2960. Min Act: -0.0000

Data Index: 1525852 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.8348. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.8289. Min Act: -0.0000

Data Index: 394760 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6802. Min Act: -0.0000

Data Index: 1277293 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5376. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.7182. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5362. Min Act: -0.0000

Data Index: 528555 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5126. Min Act: -0.0000

Data Index: 690569 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3968. Min Act: -0.0000

Data Index: 789309 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.4645. Min Act: -0.0000

Data Index: 428608 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5584. Min Act: -0.0000

Data Index: 650712 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1236545 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.4695. Min Act: -0.0000

Data Index: 536388 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1568652 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5259. Min Act: -0.0000

Data Index: 884168 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1247169 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.4208. Min Act: -0.0000

Data Index: 239852 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3126. Min Act: -0.0000

Data Index: 268502 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1258883 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.3851. Min Act: -0.0000

Data Index: 472678 (C4 (Web Text))

Max Activating Token Index: 317