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

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

Neuron 1931 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1652434 (Python Code)

Max Activating Token Index: 744

Text #1

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4846. Min Act: -0.0000

Data Index: 574701 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1351625 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1325993 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1122892 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1082059 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4565. Min Act: -0.0000

Data Index: 158841 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4756. Min Act: -0.0000

Data Index: 950390 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1315791 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4145. Min Act: -0.0000

Data Index: 832940 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1128945 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4332. Min Act: -0.0000

Data Index: 902677 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4346. Min Act: -0.0000

Data Index: 434905 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1340785 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1325419 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4129. Min Act: -0.0000

Data Index: 473877 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4024. Min Act: -0.0000

Data Index: 691685 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3929. Min Act: -0.0000

Data Index: 340568 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1387716 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 0.5591. Min Range: -0.5591

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1316076 (C4 (Web Text))

Max Activating Token Index: 495