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

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

Neuron 848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1521411 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.2200. Min Act: -0.0000

Data Index: 77931 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1580524 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1439123 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1541069 (Python Code)

Max Activating Token Index: 174

Text #5

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.0668. Min Act: -0.0000

Data Index: 842006 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.3007. Min Range: -1.3007

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1499673 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1591949 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9896. Min Act: -0.0000

Data Index: 821155 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1578729 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1216074 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1594980 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1625224 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1465234 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9880. Min Act: -0.0000

Data Index: 462653 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9047. Min Act: -0.0000

Data Index: 355288 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1272240 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1294702 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1433316 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 1.3007. Min Range: -1.3007

Max Act: 0.8500. Min Act: -0.0000

Data Index: 210135 (C4 (Web Text))

Max Activating Token Index: 13