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

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

Neuron 2347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3173. Min Act: -0.0002

Data Index: 787321 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3397. Min Act: -0.0002

Data Index: 1006015 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2885. Min Act: -0.0002

Data Index: 1645692 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3663. Min Act: -0.0002

Data Index: 619553 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2933. Min Act: -0.0002

Data Index: 1112766 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3178. Min Act: -0.0002

Data Index: 1419888 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3097. Min Act: -0.0002

Data Index: 91574 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3663. Min Act: -0.0002

Data Index: 1390465 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2977. Min Act: -0.0002

Data Index: 447252 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2970. Min Act: -0.0002

Data Index: 717068 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2933. Min Act: -0.0002

Data Index: 1376228 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2897. Min Act: -0.0002

Data Index: 1420769 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2874. Min Act: -0.0002

Data Index: 616016 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2683. Min Act: -0.0002

Data Index: 888148 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2869. Min Act: -0.0002

Data Index: 1723 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2823. Min Act: -0.0002

Data Index: 1168599 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2692. Min Act: -0.0002

Data Index: 829094 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2441. Min Act: -0.0002

Data Index: 147480 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2601. Min Act: -0.0002

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2542. Min Act: -0.0002

Data Index: 861670 (C4 (Web Text))

Max Activating Token Index: 280