Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1521302 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1607881 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1597805 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1411205 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1494382 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1565937 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1480853 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1382516 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1552244 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1389571 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1390630 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1398783 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1548214 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1560650 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1365871 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1647447 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1441126 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1516548 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1629157 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1422353 (Python Code)

Max Activating Token Index: 157