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

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

Neuron 3619 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.7257. Min Act: -0.0001

Data Index: 1279460 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.6267. Min Act: -0.0001

Data Index: 1003181 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.6700. Min Act: -0.0001

Data Index: 937508 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.5155. Min Act: -0.0001

Data Index: 829244 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4209. Min Act: -0.0001

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4228. Min Act: -0.0001

Data Index: 9430 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4159. Min Act: -0.0001

Data Index: 185727 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3721. Min Act: -0.0001

Data Index: 580041 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3652. Min Act: -0.0001

Data Index: 790180 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.5280. Min Act: -0.0001

Data Index: 1280968 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4058. Min Act: -0.0001

Data Index: 222676 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4473. Min Act: -0.0001

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.4286. Min Act: -0.0001

Data Index: 273451 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3762. Min Act: -0.0001

Data Index: 598948 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3126. Min Act: -0.0001

Data Index: 70806 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3978. Min Act: -0.0001

Data Index: 1292493 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3378. Min Act: -0.0001

Data Index: 1096851 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.3351. Min Act: -0.0001

Data Index: 192141 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.2700. Min Act: -0.0001

Data Index: 398020 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.7257. Min Range: -1.7257

Max Act: 1.2904. Min Act: -0.0001

Data Index: 1040201 (C4 (Web Text))

Max Activating Token Index: 160