Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 286412 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7667. Min Act: -0.0001

Data Index: 999333 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7549. Min Act: -0.0001

Data Index: 406034 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6879. Min Act: -0.0001

Data Index: 130925 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6993. Min Act: -0.0001

Data Index: 1096950 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1018923 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1290971 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7029. Min Act: -0.0001

Data Index: 246559 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6323. Min Act: -0.0000

Data Index: 119478 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5943. Min Act: -0.0001

Data Index: 26486 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1278976 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1323302 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5354. Min Act: -0.0001

Data Index: 472842 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5816. Min Act: -0.0000

Data Index: 386121 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1334631 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5665. Min Act: -0.0000

Data Index: 834591 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5832. Min Act: -0.0001

Data Index: 225655 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5708. Min Act: -0.0001

Data Index: 350783 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1083709 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1232902 (C4 (Web Text))

Max Activating Token Index: 507