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

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

Neuron 3343 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9975. Min Act: -0.0000

Data Index: 389530 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: 0.0000

Data Index: 802800 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1576775 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9623. Min Act: -0.0000

Data Index: 979608 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8385. Min Act: -0.0000

Data Index: 635484 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8625. Min Act: -0.0000

Data Index: 375756 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1161930 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8831. Min Act: -0.0000

Data Index: 62914 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7714. Min Act: -0.0000

Data Index: 478244 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1046594 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1349546 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7335. Min Act: -0.0000

Data Index: 930518 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1369145 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1521973 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1317328 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7586. Min Act: -0.0000

Data Index: 964406 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7458. Min Act: -0.0000

Data Index: 735718 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7791. Min Act: -0.0000

Data Index: 684559 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7513. Min Act: -0.0000

Data Index: 700882 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1578513 (Python Code)

Max Activating Token Index: 858