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

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

Neuron 5831 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: 0.9178. Min Range: -0.9178

Max Act: 0.9178. Min Act: -0.0000

Data Index: 247695 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8215. Min Act: -0.0000

Data Index: 486830 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7864. Min Act: -0.0000

Data Index: 538849 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6863. Min Act: -0.0000

Data Index: 754008 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7443. Min Act: -0.0000

Data Index: 771580 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1023068 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1308316 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6799. Min Act: -0.0000

Data Index: 233612 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1254696 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6447. Min Act: -0.0000

Data Index: 897105 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6835. Min Act: -0.0000

Data Index: 24002 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6763. Min Act: -0.0000

Data Index: 358849 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6784. Min Act: -0.0000

Data Index: 234698 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6003. Min Act: -0.0000

Data Index: 122188 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1237877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6255. Min Act: -0.0000

Data Index: 239469 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6514. Min Act: -0.0000

Data Index: 52354 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6016. Min Act: -0.0000

Data Index: 540629 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5980. Min Act: -0.0000

Data Index: 989848 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1024969 (C4 (Web Text))

Max Activating Token Index: 445