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

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

Neuron 2429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.9965. Min Act: -0.0000

Data Index: 507330 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.5754. Min Act: -0.0000

Data Index: 946977 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.7520. Min Act: -0.0000

Data Index: 416410 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.2833. Min Act: -0.0000

Data Index: 698843 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.3135. Min Act: -0.0000

Data Index: 1130024 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.4163. Min Act: -0.0000

Data Index: 999220 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.3758. Min Act: -0.0000

Data Index: 1020781 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.0674. Min Act: -0.0000

Data Index: 102976 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.3667. Min Act: -0.0000

Data Index: 120662 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.2052. Min Act: -0.0000

Data Index: 589960 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.3188. Min Act: -0.0000

Data Index: 703530 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.3262. Min Act: -0.0000

Data Index: 211827 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.1526. Min Act: -0.0000

Data Index: 674663 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.0658. Min Act: -0.0000

Data Index: 745898 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.0219. Min Act: -0.0000

Data Index: 71014 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 2.9965. Min Range: -2.9965

Max Act: 1.7556. Min Act: -0.0000

Data Index: 1066754 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.0710. Min Act: -0.0000

Data Index: 1228385 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.1865. Min Act: -0.0000

Data Index: 854771 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 2.9965. Min Range: -2.9965

Max Act: 2.1650. Min Act: -0.0000

Data Index: 887193 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 2.9965. Min Range: -2.9965

Max Act: 1.9674. Min Act: -0.0000

Data Index: 830412 (C4 (Web Text))

Max Activating Token Index: 317