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

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

Neuron 3915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.9948. Min Act: -0.0000

Data Index: 727606 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.8096. Min Act: -0.0000

Data Index: 209543 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.4105. Min Act: -0.0000

Data Index: 297026 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.5186. Min Act: -0.0000

Data Index: 244941 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.4020. Min Act: -0.0000

Data Index: 921374 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.3272. Min Act: -0.0000

Data Index: 17591 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.2992. Min Act: -0.0000

Data Index: 639246 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.1551. Min Act: -0.0000

Data Index: 67405 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.3938. Min Act: -0.0000

Data Index: 1330941 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.0422. Min Act: -0.0000

Data Index: 417870 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.3299. Min Act: -0.0000

Data Index: 532078 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.0785. Min Act: -0.0000

Data Index: 485066 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.1493. Min Act: -0.0000

Data Index: 274678 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.2448. Min Act: -0.0000

Data Index: 911156 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 2.9948. Min Range: -2.9948

Max Act: 2.2050. Min Act: -0.0000

Data Index: 1070191 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.9948. Min Range: -2.9948

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1029701 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 2.9948. Min Range: -2.9948

Max Act: 1.9143. Min Act: -0.0000

Data Index: 276387 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 2.9948. Min Range: -2.9948

Max Act: 1.8945. Min Act: -0.0000

Data Index: 90620 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 2.9948. Min Range: -2.9948

Max Act: 1.8823. Min Act: -0.0000

Data Index: 564162 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 2.9948. Min Range: -2.9948

Max Act: 1.8360. Min Act: -0.0000

Data Index: 1052519 (C4 (Web Text))

Max Activating Token Index: 375