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

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

Neuron 5899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1012354 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1080821 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.9760. Min Act: -0.0000

Data Index: 468940 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.8188. Min Act: -0.0000

Data Index: 969569 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1501930 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1438429 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1614185 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1371632 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6524. Min Act: -0.0000

Data Index: 1623934 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1043950 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6467. Min Act: -0.0000

Data Index: 1602246 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.4649. Min Act: -0.0000

Data Index: 556472 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5971. Min Act: -0.0000

Data Index: 880983 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6802. Min Act: -0.0000

Data Index: 812522 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1318015 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5725. Min Act: -0.0000

Data Index: 823075 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1385214 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1502080 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5847. Min Act: -0.0000

Data Index: 465048 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1454360 (Python Code)

Max Activating Token Index: 130