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

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

Neuron 1727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4529. Min Range: -4.4529

Max Act: 4.4529. Min Act: -0.0000

Data Index: 497385 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.7459. Min Act: -0.0000

Data Index: 1553041 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.4192. Min Act: -0.0000

Data Index: 1298380 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.5610. Min Act: -0.0000

Data Index: 422319 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.3085. Min Act: -0.0000

Data Index: 166167 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.1918. Min Act: -0.0000

Data Index: 1194496 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.9856. Min Act: -0.0000

Data Index: 620537 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.0947. Min Act: -0.0000

Data Index: 1290824 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.0685. Min Act: -0.0000

Data Index: 1105901 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.1586. Min Act: -0.0000

Data Index: 1222789 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 4.4529. Min Range: -4.4529

Max Act: 3.3018. Min Act: -0.0000

Data Index: 566982 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.6620. Min Act: -0.0000

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.9683. Min Act: -0.0000

Data Index: 1101895 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.9835. Min Act: -0.0000

Data Index: 1420825 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.7546. Min Act: -0.0000

Data Index: 1514941 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.8952. Min Act: -0.0000

Data Index: 410045 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.7302. Min Act: -0.0000

Data Index: 963352 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.7106. Min Act: -0.0000

Data Index: 1275645 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.6778. Min Act: -0.0000

Data Index: 65103 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 4.4529. Min Range: -4.4529

Max Act: 2.5175. Min Act: -0.0000

Data Index: 319552 (C4 (Web Text))

Max Activating Token Index: 433