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

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

Neuron 3438 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.4458. Min Act: -0.0000

Data Index: 1571137 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.3664. Min Act: -0.0000

Data Index: 399159 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.4455. Min Act: -0.0000

Data Index: 415811 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.3210. Min Act: -0.0000

Data Index: 1641230 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1375971 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.3804. Min Act: -0.0000

Data Index: 672762 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0859. Min Act: -0.0000

Data Index: 994600 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0287. Min Act: -0.0000

Data Index: 152785 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1514086 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1748. Min Act: -0.0000

Data Index: 464260 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0701. Min Act: -0.0000

Data Index: 1200817 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.9251. Min Act: -0.0000

Data Index: 195254 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0362. Min Act: -0.0000

Data Index: 181351 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1576608 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.9945. Min Act: -0.0000

Data Index: 40251 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0079. Min Act: -0.0000

Data Index: 796989 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1156. Min Act: -0.0000

Data Index: 713115 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.9836. Min Act: -0.0000

Data Index: 523534 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.9610. Min Act: -0.0000

Data Index: 132338 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 2.4458. Min Range: -2.4458

Max Act: 1.9778. Min Act: -0.0000

Data Index: 1591065 (Python Code)

Max Activating Token Index: 522