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

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

Neuron 3658 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9127. Min Range: -5.9127

Max Act: 5.9127. Min Act: -0.0001

Data Index: 1188573 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.5400. Min Act: -0.0001

Data Index: 1241546 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.4820. Min Act: -0.0001

Data Index: 40291 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.6583. Min Act: -0.0001

Data Index: 626395 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.4667. Min Act: -0.0001

Data Index: 312104 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.8042. Min Act: -0.0001

Data Index: 777194 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.2260. Min Act: -0.0001

Data Index: 1324771 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.2297. Min Act: -0.0001

Data Index: 314441 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.4168. Min Act: -0.0001

Data Index: 1234429 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.2161. Min Act: -0.0001

Data Index: 876128 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.9751. Min Act: -0.0001

Data Index: 277250 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.1160. Min Act: -0.0001

Data Index: 1243689 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.4811. Min Act: -0.0001

Data Index: 20567 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.5407. Min Act: -0.0001

Data Index: 1078452 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.5460. Min Act: -0.0001

Data Index: 689644 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.6948. Min Act: -0.0001

Data Index: 861726 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.7824. Min Act: -0.0001

Data Index: 749736 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 5.9127. Min Range: -5.9127

Max Act: 4.0592. Min Act: -0.0001

Data Index: 89016 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.5409. Min Act: -0.0001

Data Index: 164788 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 5.9127. Min Range: -5.9127

Max Act: 3.6946. Min Act: -0.0001

Data Index: 625453 (C4 (Web Text))

Max Activating Token Index: 914