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

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

Neuron 3454 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5064. Min Range: -2.5064

Max Act: 2.5064. Min Act: -0.0000

Data Index: 582923 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 2.5064. Min Range: -2.5064

Max Act: 2.2017. Min Act: -0.0000

Data Index: 1299409 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.5064. Min Range: -2.5064

Max Act: 1.5468. Min Act: -0.0000

Data Index: 736766 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 2.5064. Min Range: -2.5064

Max Act: 1.3063. Min Act: 0.0000

Data Index: 431198 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.9703. Min Act: -0.0000

Data Index: 889566 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.8917. Min Act: -0.0000

Data Index: 953310 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.8470. Min Act: 0.0000

Data Index: 419652 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1325484 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.7865. Min Act: -0.0000

Data Index: 968402 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.7405. Min Act: -0.0000

Data Index: 273664 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.7660. Min Act: -0.0000

Data Index: 568224 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6689. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6277. Min Act: -0.0000

Data Index: 929485 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6527. Min Act: -0.0000

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1109764 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6105. Min Act: -0.0000

Data Index: 744205 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6413. Min Act: 0.0000

Data Index: 442425 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.6291. Min Act: 0.0000

Data Index: 1187697 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 2.5064. Min Range: -2.5064

Max Act: 0.5929. Min Act: -0.0000

Data Index: 338827 (C4 (Web Text))

Max Activating Token Index: 397