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

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

Neuron 5048 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: 4.2405. Min Range: -4.2405

Max Act: 4.2405. Min Act: -0.0001

Data Index: 219055 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 4.2405. Min Range: -4.2405

Max Act: 4.0403. Min Act: -0.0001

Data Index: 519220 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.5801. Min Act: -0.0001

Data Index: 1348100 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 4.2405. Min Range: -4.2405

Max Act: 4.1702. Min Act: -0.0001

Data Index: 1325635 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 4.2405. Min Range: -4.2405

Max Act: 4.1476. Min Act: -0.0001

Data Index: 1182070 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 4.2405. Min Range: -4.2405

Max Act: 4.1587. Min Act: -0.0001

Data Index: 1357908 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.7951. Min Act: -0.0001

Data Index: 290244 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.9336. Min Act: -0.0001

Data Index: 1319608 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.8387. Min Act: -0.0001

Data Index: 301430 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.6205. Min Act: -0.0001

Data Index: 62159 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.7380. Min Act: -0.0001

Data Index: 1299279 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.6203. Min Act: -0.0001

Data Index: 631587 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 4.2405. Min Range: -4.2405

Max Act: 2.9050. Min Act: -0.0001

Data Index: 92305 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.9311. Min Act: -0.0001

Data Index: 607297 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.5452. Min Act: -0.0001

Data Index: 1359149 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.2411. Min Act: -0.0001

Data Index: 183871 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.6661. Min Act: -0.0001

Data Index: 963808 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.6429. Min Act: -0.0001

Data Index: 58879 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.4895. Min Act: -0.0001

Data Index: 990188 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 4.2405. Min Range: -4.2405

Max Act: 3.3768. Min Act: -0.0001

Data Index: 29379 (C4 (Web Text))

Max Activating Token Index: 760