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

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

Neuron 837 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: 2.3751. Min Range: -2.3751

Max Act: 2.3751. Min Act: -0.0002

Data Index: 599585 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.2952. Min Act: -0.0002

Data Index: 775543 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.1872. Min Act: -0.0002

Data Index: 207687 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.1421. Min Act: -0.0002

Data Index: 551437 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.1909. Min Act: -0.0002

Data Index: 307417 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.1909. Min Act: -0.0002

Data Index: 178318 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0547. Min Act: -0.0002

Data Index: 364778 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0425. Min Act: -0.0002

Data Index: 966142 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0598. Min Act: -0.0002

Data Index: 506645 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0401. Min Act: -0.0002

Data Index: 1069860 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0229. Min Act: -0.0002

Data Index: 165087 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0377. Min Act: -0.0002

Data Index: 1067345 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0233. Min Act: -0.0002

Data Index: 1152518 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.9926. Min Act: -0.0002

Data Index: 654891 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.9482. Min Act: -0.0002

Data Index: 379100 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.9378. Min Act: -0.0002

Data Index: 334342 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 2.3751. Min Range: -2.3751

Max Act: 2.0289. Min Act: -0.0002

Data Index: 683833 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.9572. Min Act: -0.0002

Data Index: 1087847 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.9383. Min Act: -0.0002

Data Index: 1319143 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 2.3751. Min Range: -2.3751

Max Act: 1.8942. Min Act: -0.0002

Data Index: 869206 (C4 (Web Text))

Max Activating Token Index: 44