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

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

Neuron 4998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7225. Min Act: -0.0000

Data Index: 698242 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1636152 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7261. Min Act: -0.0000

Data Index: 684219 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1134862 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1449073 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1021562 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1567904 (Python Code)

Max Activating Token Index: 165

Text #7

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5743. Min Act: -0.0000

Data Index: 104982 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1156324 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1100976 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5328. Min Act: -0.0000

Data Index: 526391 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5536. Min Act: -0.0000

Data Index: 339909 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4802. Min Act: -0.0000

Data Index: 593520 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4400. Min Act: -0.0000

Data Index: 734261 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4851. Min Act: -0.0000

Data Index: 895313 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4315. Min Act: -0.0000

Data Index: 950672 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1358906 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4596. Min Act: -0.0000

Data Index: 264200 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4672. Min Act: -0.0000

Data Index: 426158 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1625417 (Python Code)

Max Activating Token Index: 615