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

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

Neuron 791 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4743. Min Range: -1.4743

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1189858 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 1.4743. Min Range: -1.4743

Max Act: 1.0790. Min Act: -0.0000

Data Index: 571063 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.4743. Min Range: -1.4743

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1011843 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.9493. Min Act: -0.0000

Data Index: 165729 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8787. Min Act: -0.0000

Data Index: 31271 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8907. Min Act: -0.0000

Data Index: 264017 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8675. Min Act: -0.0000

Data Index: 254853 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8677. Min Act: -0.0000

Data Index: 703566 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8271. Min Act: -0.0000

Data Index: 853380 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1166148 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.7422. Min Act: -0.0000

Data Index: 882762 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6804. Min Act: -0.0000

Data Index: 315372 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.7478. Min Act: -0.0000

Data Index: 784927 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.7054. Min Act: -0.0000

Data Index: 53859 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1115861 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.7175. Min Act: -0.0000

Data Index: 337743 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6180. Min Act: -0.0000

Data Index: 787147 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6621. Min Act: -0.0000

Data Index: 823394 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6226. Min Act: -0.0000

Data Index: 72684 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 1.4743. Min Range: -1.4743

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1218900 (C4 (Web Text))

Max Activating Token Index: 836