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

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

Neuron 4875 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.5028. Min Act: -0.0000

Data Index: 992725 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.2671. Min Act: -0.0000

Data Index: 968132 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.0813. Min Act: -0.0000

Data Index: 760898 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.1409. Min Act: -0.0000

Data Index: 113512 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9715. Min Act: -0.0000

Data Index: 624124 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.1594. Min Act: -0.0000

Data Index: 174999 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.0147. Min Act: -0.0000

Data Index: 860368 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.5028. Min Range: -1.5028

Max Act: 1.0102. Min Act: -0.0000

Data Index: 331550 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1059387 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1317479 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1349576 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9289. Min Act: -0.0000

Data Index: 943420 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9302. Min Act: -0.0000

Data Index: 197144 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9450. Min Act: -0.0000

Data Index: 195296 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.8335. Min Act: -0.0000

Data Index: 501630 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1305988 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1238186 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.8748. Min Act: -0.0000

Data Index: 921642 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.8130. Min Act: -0.0000

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.5028. Min Range: -1.5028

Max Act: 0.8099. Min Act: -0.0000

Data Index: 235518 (C4 (Web Text))

Max Activating Token Index: 465