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

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

Neuron 1204 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3036. Min Range: -1.3036

Max Act: 1.3036. Min Act: -0.0001

Data Index: 374809 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.3036. Min Range: -1.3036

Max Act: 1.0427. Min Act: -0.0001

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.3036. Min Range: -1.3036

Max Act: 1.0983. Min Act: -0.0001

Data Index: 1153855 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9945. Min Act: -0.0001

Data Index: 634638 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9513. Min Act: -0.0001

Data Index: 1217511 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9170. Min Act: -0.0001

Data Index: 685962 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9121. Min Act: -0.0001

Data Index: 877287 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8774. Min Act: -0.0001

Data Index: 1256986 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9825. Min Act: -0.0001

Data Index: 1022796 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.9004. Min Act: -0.0001

Data Index: 86227 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8406. Min Act: -0.0001

Data Index: 720291 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8326. Min Act: -0.0001

Data Index: 375081 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.7810. Min Act: -0.0001

Data Index: 318285 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8780. Min Act: -0.0001

Data Index: 446793 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.7742. Min Act: -0.0001

Data Index: 632032 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8258. Min Act: -0.0001

Data Index: 469719 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8170. Min Act: -0.0001

Data Index: 426496 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.7162. Min Act: -0.0001

Data Index: 75511 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.7776. Min Act: -0.0001

Data Index: 478946 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.3036. Min Range: -1.3036

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1001007 (C4 (Web Text))

Max Activating Token Index: 517