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

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

Neuron 4113 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8821. Min Range: -2.8821

Max Act: 2.8821. Min Act: -0.0000

Data Index: 935321 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.8821. Min Range: -2.8821

Max Act: 2.6737. Min Act: -0.0000

Data Index: 425076 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.8821. Min Range: -2.8821

Max Act: 2.3568. Min Act: -0.0000

Data Index: 1187503 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 2.8821. Min Range: -2.8821

Max Act: 2.3412. Min Act: -0.0000

Data Index: 385497 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.8821. Min Range: -2.8821

Max Act: 2.1498. Min Act: -0.0000

Data Index: 1257836 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.9120. Min Act: -0.0000

Data Index: 1356325 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.7884. Min Act: -0.0000

Data Index: 338753 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1352226 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.6448. Min Act: -0.0000

Data Index: 80123 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.5140. Min Act: -0.0000

Data Index: 851056 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.4266. Min Act: -0.0000

Data Index: 683835 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.4040. Min Act: -0.0000

Data Index: 672480 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.5159. Min Act: -0.0000

Data Index: 652592 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 2.8821. Min Range: -2.8821

Max Act: 1.0497. Min Act: -0.0000

Data Index: 501754 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.8664. Min Act: -0.0000

Data Index: 378953 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.9871. Min Act: -0.0000

Data Index: 220201 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.9057. Min Act: -0.0000

Data Index: 192049 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1308672 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1227043 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 2.8821. Min Range: -2.8821

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1236498 (C4 (Web Text))

Max Activating Token Index: 750