Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4900. Min Act: -0.0001

Data Index: 1337311 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4641. Min Act: -0.0001

Data Index: 865738 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4752. Min Act: -0.0001

Data Index: 72006 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4291. Min Act: -0.0001

Data Index: 639597 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4280. Min Act: -0.0001

Data Index: 1006803 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3986. Min Act: -0.0001

Data Index: 619562 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4123. Min Act: -0.0001

Data Index: 887005 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4226. Min Act: -0.0001

Data Index: 411766 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4173. Min Act: -0.0001

Data Index: 832643 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.4052. Min Act: -0.0001

Data Index: 606060 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3915. Min Act: -0.0001

Data Index: 1074046 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3885. Min Act: -0.0001

Data Index: 301220 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3875. Min Act: -0.0001

Data Index: 1202040 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1038892 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3819. Min Act: -0.0001

Data Index: 468714 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3736. Min Act: -0.0001

Data Index: 363115 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3875. Min Act: -0.0001

Data Index: 343070 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3908. Min Act: -0.0001

Data Index: 429530 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3768. Min Act: -0.0001

Data Index: 816669 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.4900. Min Range: -0.4900

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1139994 (C4 (Web Text))

Max Activating Token Index: 451