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

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

Neuron 1718 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1189686 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4849. Min Act: -0.0000

Data Index: 96810 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4604. Min Act: -0.0000

Data Index: 288287 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4156. Min Act: -0.0000

Data Index: 279791 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1611178 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4090. Min Act: -0.0000

Data Index: 293392 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1286811 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1544208 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4008. Min Act: -0.0000

Data Index: 589748 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1144272 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3714. Min Act: -0.0000

Data Index: 950264 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1057271 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3945. Min Act: -0.0000

Data Index: 313853 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1238274 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4042. Min Act: -0.0000

Data Index: 461812 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.4160. Min Act: -0.0000

Data Index: 186908 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1093224 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1218773 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1498312 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 0.5396. Min Range: -0.5396

Max Act: 0.3547. Min Act: -0.0000

Data Index: 869272 (C4 (Web Text))

Max Activating Token Index: 217