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

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

Neuron 4064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0002

Data Index: 849140 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0682. Min Act: -0.0002

Data Index: 969522 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0683. Min Act: -0.0002

Data Index: 243053 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0652. Min Act: -0.0002

Data Index: 697537 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0583. Min Act: -0.0002

Data Index: 340885 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0579. Min Act: -0.0002

Data Index: 993811 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1342906 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0571. Min Act: -0.0002

Data Index: 634187 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0526. Min Act: -0.0002

Data Index: 920873 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1258460 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0543. Min Act: -0.0002

Data Index: 483038 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0511. Min Act: -0.0002

Data Index: 920073 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1197357 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1065344 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1075073 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1309861 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1599320 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0501. Min Act: -0.0002

Data Index: 393024 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0444. Min Act: -0.0002

Data Index: 472334 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0481. Min Act: -0.0002

Data Index: 422952 (C4 (Web Text))

Max Activating Token Index: 508