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

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

Neuron 6136 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7598. Min Act: -0.0001

Data Index: 505157 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6925. Min Act: -0.0001

Data Index: 181571 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6874. Min Act: -0.0001

Data Index: 54749 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5771. Min Act: -0.0001

Data Index: 943539 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6252. Min Act: -0.0001

Data Index: 580835 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5858. Min Act: -0.0001

Data Index: 681262 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5723. Min Act: -0.0001

Data Index: 773809 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5828. Min Act: -0.0001

Data Index: 860017 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5427. Min Act: -0.0001

Data Index: 625240 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5615. Min Act: -0.0001

Data Index: 491051 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1033908 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5022. Min Act: -0.0001

Data Index: 952697 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5155. Min Act: -0.0001

Data Index: 98192 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5239. Min Act: -0.0001

Data Index: 546557 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5365. Min Act: -0.0001

Data Index: 1345703 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5712. Min Act: -0.0001

Data Index: 36064 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5303. Min Act: -0.0001

Data Index: 1083280 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4847. Min Act: -0.0001

Data Index: 957057 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.4746. Min Act: -0.0001

Data Index: 291036 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1035129 (C4 (Web Text))

Max Activating Token Index: 258