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

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

Neuron 5858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1180. Min Range: -1.1180

Max Act: 1.1180. Min Act: -0.0001

Data Index: 938479 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1039672 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7976. Min Act: -0.0001

Data Index: 409216 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7158. Min Act: -0.0000

Data Index: 841409 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.9511. Min Act: -0.0000

Data Index: 51579 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.9697. Min Act: -0.0001

Data Index: 468082 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8360. Min Act: -0.0000

Data Index: 473173 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8663. Min Act: -0.0000

Data Index: 596670 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8390. Min Act: -0.0000

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.9085. Min Act: -0.0000

Data Index: 710681 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7154. Min Act: -0.0001

Data Index: 662861 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7568. Min Act: -0.0000

Data Index: 824781 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1159245 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8483. Min Act: -0.0001

Data Index: 348921 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1093592 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.5948. Min Act: -0.0000

Data Index: 846949 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8390. Min Act: -0.0000

Data Index: 913330 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.8314. Min Act: -0.0000

Data Index: 694525 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7800. Min Act: -0.0000

Data Index: 801839 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 1.1180. Min Range: -1.1180

Max Act: 0.7771. Min Act: -0.0000

Data Index: 296471 (C4 (Web Text))

Max Activating Token Index: 141