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

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

Neuron 1250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1261754 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6659. Min Act: -0.0000

Data Index: 606095 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7196. Min Act: -0.0000

Data Index: 204491 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.7040. Min Act: -0.0000

Data Index: 150759 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6480. Min Act: -0.0001

Data Index: 507099 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6584. Min Act: -0.0001

Data Index: 71008 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6211. Min Act: -0.0000

Data Index: 666719 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6237. Min Act: -0.0000

Data Index: 965511 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5820. Min Act: -0.0000

Data Index: 787138 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1152032 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.6035. Min Act: -0.0000

Data Index: 887827 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5629. Min Act: -0.0000

Data Index: 244330 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1022996 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5835. Min Act: -0.0000

Data Index: 306138 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1162842 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5600. Min Act: -0.0000

Data Index: 616742 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5026. Min Act: -0.0000

Data Index: 940136 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5355. Min Act: -0.0001

Data Index: 614277 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5182. Min Act: -0.0001

Data Index: 494236 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.7570. Min Range: -0.7570

Max Act: 0.5305. Min Act: -0.0000

Data Index: 44740 (C4 (Web Text))

Max Activating Token Index: 122