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

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

Neuron 5854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1104151 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0662. Min Act: -0.0000

Data Index: 77226 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0545. Min Act: -0.0001

Data Index: 468800 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0614. Min Act: -0.0001

Data Index: 962838 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0545. Min Act: -0.0001

Data Index: 565781 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0580. Min Act: -0.0001

Data Index: 911133 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0547. Min Act: -0.0000

Data Index: 277064 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0521. Min Act: -0.0000

Data Index: 220725 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0514. Min Act: -0.0001

Data Index: 412845 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1063253 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0491. Min Act: -0.0000

Data Index: 742859 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0475. Min Act: -0.0000

Data Index: 935329 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0525. Min Act: -0.0001

Data Index: 956168 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0503. Min Act: -0.0000

Data Index: 409226 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0526. Min Act: -0.0000

Data Index: 971966 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0505. Min Act: -0.0000

Data Index: 982163 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0495. Min Act: -0.0001

Data Index: 309889 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1047385 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0507. Min Act: -0.0000

Data Index: 245552 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0458. Min Act: -0.0001

Data Index: 840831 (C4 (Web Text))

Max Activating Token Index: 8