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

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

Neuron 5079 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: 4.9400. Min Range: -4.9400

Max Act: 4.9400. Min Act: -0.0000

Data Index: 954679 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 4.9400. Min Range: -4.9400

Max Act: 4.4598. Min Act: -0.0000

Data Index: 497526 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 4.9400. Min Range: -4.9400

Max Act: 4.2860. Min Act: -0.0001

Data Index: 663551 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 4.9400. Min Range: -4.9400

Max Act: 4.1462. Min Act: -0.0001

Data Index: 614329 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 4.9400. Min Range: -4.9400

Max Act: 4.1119. Min Act: -0.0000

Data Index: 1251133 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 4.9400. Min Range: -4.9400

Max Act: 4.0147. Min Act: -0.0001

Data Index: 356685 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7865. Min Act: -0.0001

Data Index: 908873 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7370. Min Act: -0.0001

Data Index: 154273 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.8505. Min Act: -0.0001

Data Index: 1218550 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.8351. Min Act: -0.0001

Data Index: 404052 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.9365. Min Act: -0.0000

Data Index: 602652 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7891. Min Act: -0.0001

Data Index: 688008 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7657. Min Act: -0.0001

Data Index: 29532 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.5769. Min Act: -0.0000

Data Index: 930727 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.5993. Min Act: -0.0001

Data Index: 1102230 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7425. Min Act: -0.0000

Data Index: 204916 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.6756. Min Act: -0.0000

Data Index: 304237 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.7302. Min Act: -0.0001

Data Index: 222020 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.6747. Min Act: -0.0001

Data Index: 1298413 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 4.9400. Min Range: -4.9400

Max Act: 3.8150. Min Act: -0.0001

Data Index: 502421 (C4 (Web Text))

Max Activating Token Index: 34