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

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

Neuron 3455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3303. Min Act: -0.0000

Data Index: 498390 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1147979 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1039250 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3149. Min Act: -0.0001

Data Index: 16317 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3048. Min Act: -0.0000

Data Index: 825713 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1031951 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2947. Min Act: -0.0000

Data Index: 131931 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1230786 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2848. Min Act: -0.0000

Data Index: 158104 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2752. Min Act: -0.0000

Data Index: 765326 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2720. Min Act: -0.0000

Data Index: 822584 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2813. Min Act: -0.0000

Data Index: 116515 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2804. Min Act: -0.0000

Data Index: 136888 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2810. Min Act: -0.0000

Data Index: 487804 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1206548 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2654. Min Act: -0.0000

Data Index: 86088 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1197370 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2704. Min Act: -0.0000

Data Index: 267459 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2608. Min Act: -0.0000

Data Index: 347785 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.3303. Min Range: -0.3303

Max Act: 0.2597. Min Act: -0.0000

Data Index: 646242 (C4 (Web Text))

Max Activating Token Index: 357