Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.3266. Min Act: -0.0001

Data Index: 147218 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1182328 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1505080 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.3153. Min Act: -0.0001

Data Index: 340975 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2818. Min Act: -0.0001

Data Index: 491767 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2746. Min Act: -0.0001

Data Index: 583505 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2794. Min Act: -0.0001

Data Index: 1561167 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1540167 (Python Code)

Max Activating Token Index: 632

Text #8

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1393490 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2503. Min Act: -0.0001

Data Index: 993796 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1055470 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1398242 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1367183 (Python Code)

Max Activating Token Index: 746

Text #13

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1532776 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2578. Min Act: -0.0001

Data Index: 782204 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1325369 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1504949 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1418064 (Python Code)

Max Activating Token Index: 714

Text #18

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1485147 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 0.3266. Min Range: -0.3266

Max Act: 0.2644. Min Act: -0.0001

Data Index: 160005 (C4 (Web Text))

Max Activating Token Index: 622