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

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

Neuron 3779 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: 0.8620. Min Range: -0.8620

Max Act: 0.8449. Min Act: -0.0001

Data Index: 565789 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.8620. Min Act: -0.0001

Data Index: 439442 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7949. Min Act: -0.0001

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7845. Min Act: -0.0000

Data Index: 582673 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.8416. Min Act: -0.0001

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.8109. Min Act: -0.0001

Data Index: 388274 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7823. Min Act: -0.0000

Data Index: 907492 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7341. Min Act: -0.0000

Data Index: 130430 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7523. Min Act: -0.0001

Data Index: 163016 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7208. Min Act: -0.0001

Data Index: 954455 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7439. Min Act: -0.0001

Data Index: 417628 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7669. Min Act: -0.0000

Data Index: 79516 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1084809 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1341074 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6938. Min Act: -0.0000

Data Index: 48850 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1219094 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7031. Min Act: -0.0001

Data Index: 790258 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6813. Min Act: -0.0001

Data Index: 1249944 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1347552 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1067621 (C4 (Web Text))

Max Activating Token Index: 148