Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2215 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1524258 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1507108 (Python Code)

Max Activating Token Index: 995

Text #2

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9621. Min Act: -0.0001

Data Index: 1645663 (Python Code)

Max Activating Token Index: 590

Text #3

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.9215. Min Act: -0.0001

Data Index: 1376922 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.8651. Min Act: -0.0001

Data Index: 1427884 (Python Code)

Max Activating Token Index: 470

Text #5

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7869. Min Act: -0.0001

Data Index: 1605297 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1424786 (Python Code)

Max Activating Token Index: 607

Text #7

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1619454 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7405. Min Act: -0.0001

Data Index: 1051762 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1471715 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1541084 (Python Code)

Max Activating Token Index: 267

Text #11

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1374638 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1603752 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7464. Min Act: -0.0001

Data Index: 1541316 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7002. Min Act: -0.0001

Data Index: 1567957 (Python Code)

Max Activating Token Index: 462

Text #15

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7174. Min Act: -0.0001

Data Index: 1390045 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1645909 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1589702 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1414621 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.9621. Min Range: -0.9621

Max Act: 0.6874. Min Act: -0.0001

Data Index: 1400494 (Python Code)

Max Activating Token Index: 270