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

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

Neuron 5832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1285233 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1336184 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4415. Min Act: -0.0000

Data Index: 514556 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4390. Min Act: -0.0000

Data Index: 654062 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1124394 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4068. Min Act: -0.0000

Data Index: 559455 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4152. Min Act: -0.0000

Data Index: 820976 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1157568 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3619. Min Act: -0.0000

Data Index: 604122 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3768. Min Act: -0.0000

Data Index: 30180 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1010150 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3666. Min Act: -0.0000

Data Index: 496277 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3789. Min Act: -0.0000

Data Index: 494677 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3556. Min Act: -0.0000

Data Index: 10510 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3460. Min Act: -0.0000

Data Index: 435058 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3215. Min Act: -0.0000

Data Index: 714834 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1343142 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3641. Min Act: -0.0000

Data Index: 299516 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1266493 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3521. Min Act: -0.0000

Data Index: 596755 (C4 (Web Text))

Max Activating Token Index: 795