Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 219 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.9051. Min Act: -0.0001

Data Index: 389288 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.9475. Min Act: -0.0001

Data Index: 1047613 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.8053. Min Act: -0.0001

Data Index: 635126 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7497. Min Act: -0.0001

Data Index: 848688 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7283. Min Act: -0.0001

Data Index: 572618 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7040. Min Act: -0.0001

Data Index: 511644 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7453. Min Act: -0.0001

Data Index: 275468 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1596420 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6610. Min Act: -0.0001

Data Index: 654304 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7172. Min Act: -0.0001

Data Index: 482248 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6600. Min Act: -0.0001

Data Index: 400805 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1580722 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6398. Min Act: -0.0001

Data Index: 657747 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6103. Min Act: -0.0001

Data Index: 666738 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1341634 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6083. Min Act: -0.0001

Data Index: 722006 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6035. Min Act: -0.0001

Data Index: 159531 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6144. Min Act: -0.0001

Data Index: 1007339 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6035. Min Act: -0.0001

Data Index: 84640 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.5737. Min Act: -0.0001

Data Index: 281944 (C4 (Web Text))

Max Activating Token Index: 869