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

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

Neuron 5334 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: 2.7474. Min Range: -2.7474

Max Act: 2.7474. Min Act: -0.0000

Data Index: 573871 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.4636. Min Act: -0.0000

Data Index: 267975 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.6229. Min Act: -0.0000

Data Index: 761481 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.1439. Min Act: -0.0000

Data Index: 1317768 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.3304. Min Act: -0.0000

Data Index: 794479 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.1012. Min Act: -0.0000

Data Index: 240770 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.2055. Min Act: -0.0000

Data Index: 1345372 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.0959. Min Act: -0.0000

Data Index: 1089110 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.0926. Min Act: -0.0000

Data Index: 332735 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.0444. Min Act: -0.0000

Data Index: 1275839 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.1088. Min Act: -0.0000

Data Index: 1152168 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.0156. Min Act: -0.0000

Data Index: 589505 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.9088. Min Act: -0.0000

Data Index: 289251 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.2211. Min Act: -0.0000

Data Index: 469216 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.7474. Min Range: -2.7474

Max Act: 2.0991. Min Act: -0.0000

Data Index: 10826 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.9948. Min Act: -0.0000

Data Index: 171228 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1315960 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.7356. Min Act: -0.0000

Data Index: 711176 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.9104. Min Act: -0.0000

Data Index: 215757 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 2.7474. Min Range: -2.7474

Max Act: 1.9866. Min Act: -0.0000

Data Index: 1043961 (C4 (Web Text))

Max Activating Token Index: 430