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

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

Neuron 3177 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1351082 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1252609 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.6712. Min Act: -0.0000

Data Index: 879177 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1103913 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.5492. Min Act: -0.0000

Data Index: 952682 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.5164. Min Act: -0.0000

Data Index: 732664 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.3431. Min Act: -0.0000

Data Index: 965748 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4663. Min Act: 0.0000

Data Index: 1261702 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.3750. Min Act: 0.0000

Data Index: 381984 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4601. Min Act: -0.0000

Data Index: 985286 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4547. Min Act: 0.0000

Data Index: 322819 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4564. Min Act: -0.0000

Data Index: 988276 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4469. Min Act: -0.0000

Data Index: 227425 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4420. Min Act: -0.0000

Data Index: 50358 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4456. Min Act: -0.0000

Data Index: 314614 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.5194. Min Act: -0.0000

Data Index: 973562 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.3343. Min Act: -0.0000

Data Index: 217336 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.3378. Min Act: -0.0000

Data Index: 520969 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4156. Min Act: -0.0000

Data Index: 229015 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.8485. Min Range: -1.8485

Max Act: 1.4008. Min Act: -0.0000

Data Index: 478125 (C4 (Web Text))

Max Activating Token Index: 388