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

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

Neuron 5135 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4255. Min Range: -4.4255

Max Act: 4.4255. Min Act: -0.0000

Data Index: 168088 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 4.4255. Min Range: -4.4255

Max Act: 3.3640. Min Act: -0.0000

Data Index: 229132 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.8157. Min Act: -0.0000

Data Index: 1098848 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 4.4255. Min Range: -4.4255

Max Act: 3.0568. Min Act: -0.0000

Data Index: 1325362 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.7956. Min Act: -0.0000

Data Index: 654061 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.8670. Min Act: -0.0000

Data Index: 1233624 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.7272. Min Act: -0.0000

Data Index: 86029 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.6931. Min Act: -0.0000

Data Index: 1117657 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.9365. Min Act: -0.0000

Data Index: 741966 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.9131. Min Act: -0.0000

Data Index: 1236449 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.6833. Min Act: -0.0000

Data Index: 576450 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.5193. Min Act: -0.0000

Data Index: 1309378 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.7856. Min Act: -0.0000

Data Index: 1143862 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.5387. Min Act: -0.0000

Data Index: 667906 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.6414. Min Act: -0.0000

Data Index: 481933 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.6204. Min Act: -0.0000

Data Index: 1203073 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.6422. Min Act: -0.0000

Data Index: 737096 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.4248. Min Act: -0.0000

Data Index: 1146908 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.4396. Min Act: -0.0000

Data Index: 1148975 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 4.4255. Min Range: -4.4255

Max Act: 2.3013. Min Act: -0.0000

Data Index: 714025 (C4 (Web Text))

Max Activating Token Index: 246