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

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

Neuron 4799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0114. Min Range: -1.0114

Max Act: 1.0114. Min Act: -0.0002

Data Index: 552755 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8314. Min Act: -0.0002

Data Index: 525646 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9593. Min Act: -0.0002

Data Index: 1022879 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8424. Min Act: -0.0002

Data Index: 393325 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8348. Min Act: -0.0002

Data Index: 538698 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8692. Min Act: -0.0002

Data Index: 816573 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.6891. Min Act: -0.0002

Data Index: 83555 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8252. Min Act: -0.0002

Data Index: 464175 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8464. Min Act: -0.0002

Data Index: 1335450 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8622. Min Act: -0.0002

Data Index: 636203 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8286. Min Act: -0.0002

Data Index: 1003926 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.9174. Min Act: -0.0002

Data Index: 318892 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8229. Min Act: -0.0002

Data Index: 887331 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8675. Min Act: -0.0002

Data Index: 163647 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8225. Min Act: -0.0002

Data Index: 249383 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7528. Min Act: -0.0002

Data Index: 133322 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7425. Min Act: -0.0002

Data Index: 929095 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8623. Min Act: -0.0002

Data Index: 608775 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.7540. Min Act: -0.0002

Data Index: 568730 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.0114. Min Range: -1.0114

Max Act: 0.8074. Min Act: -0.0002

Data Index: 474751 (C4 (Web Text))

Max Activating Token Index: 669