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

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

Neuron 1653 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: 0.2845. Min Range: -0.2845

Max Act: 0.2798. Min Act: -0.0001

Data Index: 349585 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2751. Min Act: -0.0001

Data Index: 493207 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2816. Min Act: -0.0001

Data Index: 178482 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1237712 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2691. Min Act: -0.0001

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2508. Min Act: -0.0001

Data Index: 693724 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2583. Min Act: -0.0001

Data Index: 872274 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2555. Min Act: -0.0001

Data Index: 337043 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2380. Min Act: -0.0001

Data Index: 836946 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2441. Min Act: -0.0001

Data Index: 382143 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2492. Min Act: -0.0001

Data Index: 15033 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1218391 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2453. Min Act: -0.0001

Data Index: 78707 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2464. Min Act: -0.0001

Data Index: 820419 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2442. Min Act: -0.0001

Data Index: 590833 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2443. Min Act: -0.0001

Data Index: 727997 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2432. Min Act: -0.0001

Data Index: 895670 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2414. Min Act: -0.0001

Data Index: 186596 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2404. Min Act: -0.0001

Data Index: 14508 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2300. Min Act: -0.0001

Data Index: 78186 (C4 (Web Text))

Max Activating Token Index: 320