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

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

Neuron 5426 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.3411. Min Act: -0.0001

Data Index: 963971 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.4123. Min Act: -0.0001

Data Index: 809010 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.1342. Min Act: -0.0001

Data Index: 1097125 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.1230. Min Act: -0.0001

Data Index: 516609 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.2449. Min Act: -0.0001

Data Index: 708265 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.4123. Min Range: -3.4123

Max Act: 3.2448. Min Act: -0.0001

Data Index: 1061599 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8760. Min Act: -0.0001

Data Index: 1188741 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.9919. Min Act: -0.0001

Data Index: 1234917 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.9751. Min Act: -0.0001

Data Index: 1309391 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.9014. Min Act: -0.0001

Data Index: 847680 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.6227. Min Act: -0.0000

Data Index: 500998 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8680. Min Act: -0.0001

Data Index: 882226 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.7317. Min Act: -0.0001

Data Index: 728149 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8670. Min Act: -0.0001

Data Index: 869298 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.6180. Min Act: -0.0001

Data Index: 1107270 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.7306. Min Act: -0.0001

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8435. Min Act: -0.0001

Data Index: 488184 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8426. Min Act: -0.0001

Data Index: 921750 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.8203. Min Act: -0.0001

Data Index: 417909 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.4123. Min Range: -3.4123

Max Act: 2.6741. Min Act: -0.0001

Data Index: 1284261 (C4 (Web Text))

Max Activating Token Index: 475