Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9784. Min Act: -0.0000

Data Index: 885516 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9876. Min Act: -0.0001

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9947. Min Act: -0.0001

Data Index: 999904 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9907. Min Act: -0.0001

Data Index: 510411 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9091. Min Act: -0.0001

Data Index: 852986 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8900. Min Act: -0.0001

Data Index: 236200 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8974. Min Act: -0.0001

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9009. Min Act: -0.0001

Data Index: 219318 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8435. Min Act: -0.0001

Data Index: 608033 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8312. Min Act: -0.0001

Data Index: 1348901 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1198087 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7877. Min Act: -0.0001

Data Index: 847183 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1167814 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8222. Min Act: -0.0001

Data Index: 619421 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8266. Min Act: -0.0001

Data Index: 503207 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7589. Min Act: -0.0001

Data Index: 576535 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1186801 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.6635. Min Act: -0.0001

Data Index: 3244 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.7361. Min Act: -0.0001

Data Index: 1185055 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8508. Min Act: -0.0001

Data Index: 733420 (C4 (Web Text))

Max Activating Token Index: 653