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

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

Neuron 3270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.3251. Min Act: -0.0000

Data Index: 995233 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.3251. Min Range: -1.3251

Max Act: 1.1577. Min Act: -0.0000

Data Index: 458188 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9713. Min Act: -0.0000

Data Index: 515187 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.9641. Min Act: -0.0000

Data Index: 289357 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8933. Min Act: -0.0000

Data Index: 76008 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8886. Min Act: -0.0000

Data Index: 508519 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8669. Min Act: -0.0000

Data Index: 47412 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8978. Min Act: -0.0000

Data Index: 944908 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8636. Min Act: -0.0000

Data Index: 603751 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7643. Min Act: -0.0000

Data Index: 431736 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8169. Min Act: -0.0000

Data Index: 321715 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8887. Min Act: -0.0000

Data Index: 616326 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8298. Min Act: -0.0001

Data Index: 1051251 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8158. Min Act: -0.0000

Data Index: 138889 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.8122. Min Act: -0.0000

Data Index: 927656 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7842. Min Act: -0.0000

Data Index: 254719 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7850. Min Act: -0.0000

Data Index: 279328 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7751. Min Act: -0.0000

Data Index: 694278 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7993. Min Act: -0.0000

Data Index: 699205 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.3251. Min Range: -1.3251

Max Act: 0.7665. Min Act: -0.0001

Data Index: 982739 (C4 (Web Text))

Max Activating Token Index: 945