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

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

Neuron 3743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1459797 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1630027 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1361533 (Python Code)

Max Activating Token Index: 937

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1420493 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1458587 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1500488 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5187. Min Act: -0.0001

Data Index: 1649451 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1448035 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1599808 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1451974 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5342. Min Act: -0.0001

Data Index: 1411500 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1479174 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1527500 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5164. Min Act: -0.0001

Data Index: 1484817 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1620026 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4971. Min Act: -0.0001

Data Index: 1629726 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1463764 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1527914 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5028. Min Act: -0.0001

Data Index: 1392772 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1653221 (Python Code)

Max Activating Token Index: 985