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

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

Neuron 839 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.5948. Min Act: -0.0002

Data Index: 125491 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4816. Min Act: -0.0002

Data Index: 1365484 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4229. Min Act: -0.0002

Data Index: 1617466 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3479. Min Act: -0.0002

Data Index: 564094 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2853. Min Act: -0.0002

Data Index: 645023 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2751. Min Act: -0.0002

Data Index: 340477 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2751. Min Act: -0.0002

Data Index: 416607 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2856. Min Act: -0.0002

Data Index: 213256 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2249. Min Act: -0.0002

Data Index: 302347 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1912. Min Act: -0.0002

Data Index: 1494289 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2070. Min Act: -0.0002

Data Index: 139569 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2318. Min Act: -0.0002

Data Index: 1379551 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2530. Min Act: -0.0002

Data Index: 431931 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2327. Min Act: -0.0002

Data Index: 1519165 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2111. Min Act: -0.0002

Data Index: 1331577 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2056. Min Act: -0.0002

Data Index: 1640161 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1719. Min Act: -0.0002

Data Index: 1364306 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1899. Min Act: -0.0002

Data Index: 120463 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1938. Min Act: -0.0002

Data Index: 1186484 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1891. Min Act: -0.0002

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 295