Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1048 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1444368 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1639509 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1415658 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1344026 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1626328 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3272. Min Act: -0.0001

Data Index: 584889 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1653600 (Python Code)

Max Activating Token Index: 602

Text #7

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1611174 (Python Code)

Max Activating Token Index: 1013

Text #8

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1414390 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2752. Min Act: -0.0001

Data Index: 192560 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2801. Min Act: -0.0001

Data Index: 1582365 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2777. Min Act: -0.0001

Data Index: 1461257 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1390699 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2401. Min Act: -0.0001

Data Index: 981383 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1433373 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2926. Min Act: -0.0001

Data Index: 1585824 (Python Code)

Max Activating Token Index: 717

Text #16

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1445315 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1402970 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1452383 (Python Code)

Max Activating Token Index: 772

Text #19

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1512745 (Python Code)

Max Activating Token Index: 952