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

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

Neuron 4391 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: 1.4768. Min Range: -1.4768

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.4768. Min Act: -0.0000

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2683. Min Act: -0.0000

Data Index: 142682 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1854. Min Act: -0.0000

Data Index: 25824 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1148250 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1581. Min Act: -0.0000

Data Index: 635652 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1651. Min Act: -0.0000

Data Index: 865924 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1922. Min Act: -0.0000

Data Index: 939153 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1057900 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1295269 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1250371 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1267. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1061. Min Act: -0.0000

Data Index: 112998 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1149950 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1622. Min Act: -0.0000

Data Index: 591141 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1331786 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1047. Min Act: -0.0000

Data Index: 167934 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1726. Min Act: -0.0000

Data Index: 801296 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1277. Min Act: -0.0000

Data Index: 399406 (C4 (Web Text))

Max Activating Token Index: 137