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

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

Neuron 3183 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: 1.5999. Min Range: -1.5999

Max Act: 1.5999. Min Act: -0.0001

Data Index: 478219 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4938. Min Act: -0.0001

Data Index: 311855 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5662. Min Act: -0.0001

Data Index: 1127217 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5996. Min Act: -0.0001

Data Index: 643912 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5278. Min Act: -0.0001

Data Index: 976969 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5160. Min Act: -0.0001

Data Index: 1051123 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5508. Min Act: -0.0001

Data Index: 1222549 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.5423. Min Act: -0.0001

Data Index: 1192897 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4844. Min Act: -0.0001

Data Index: 428976 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4362. Min Act: -0.0001

Data Index: 172496 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4676. Min Act: -0.0001

Data Index: 1256781 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4483. Min Act: -0.0001

Data Index: 612893 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3734. Min Act: -0.0001

Data Index: 83982 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4427. Min Act: -0.0001

Data Index: 156980 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.2987. Min Act: -0.0001

Data Index: 139506 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4433. Min Act: -0.0001

Data Index: 127340 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.3597. Min Act: -0.0001

Data Index: 787976 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4065. Min Act: -0.0001

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4822. Min Act: -0.0001

Data Index: 773580 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.5999. Min Range: -1.5999

Max Act: 1.4168. Min Act: -0.0001

Data Index: 302376 (C4 (Web Text))

Max Activating Token Index: 637