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

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

Neuron 4645 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.5405. Min Act: -0.0000

Data Index: 239664 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.3459. Min Act: -0.0000

Data Index: 641425 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.1810. Min Act: -0.0000

Data Index: 168138 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.1631. Min Act: -0.0000

Data Index: 291080 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1282407 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.1036. Min Act: -0.0000

Data Index: 523623 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0611. Min Act: -0.0000

Data Index: 552860 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.1160. Min Act: -0.0000

Data Index: 437277 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9511. Min Act: -0.0000

Data Index: 708429 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0395. Min Act: -0.0000

Data Index: 639424 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9419. Min Act: -0.0000

Data Index: 195802 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0311. Min Act: -0.0000

Data Index: 48310 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1343302 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9971. Min Act: -0.0000

Data Index: 576149 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0034. Min Act: -0.0000

Data Index: 445945 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9331. Min Act: -0.0000

Data Index: 97077 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9806. Min Act: -0.0000

Data Index: 777304 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1020020 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.5405. Min Range: -1.5405

Max Act: 1.0017. Min Act: -0.0000

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.5405. Min Range: -1.5405

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1039407 (C4 (Web Text))

Max Activating Token Index: 899