Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7047. Min Act: -0.0003

Data Index: 380551 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7512. Min Act: -0.0003

Data Index: 162044 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6241. Min Act: -0.0003

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5908. Min Act: -0.0003

Data Index: 733583 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5660. Min Act: -0.0003

Data Index: 210834 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6019. Min Act: -0.0003

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5282. Min Act: -0.0003

Data Index: 607046 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5139. Min Act: -0.0003

Data Index: 1333143 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5348. Min Act: -0.0003

Data Index: 210085 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5294. Min Act: -0.0003

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5266. Min Act: -0.0003

Data Index: 693304 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5113. Min Act: -0.0003

Data Index: 905361 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5000. Min Act: -0.0003

Data Index: 675402 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5190. Min Act: -0.0003

Data Index: 617795 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4673. Min Act: -0.0003

Data Index: 444444 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4660. Min Act: -0.0003

Data Index: 1121263 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4927. Min Act: -0.0003

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4596. Min Act: -0.0003

Data Index: 474136 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4537. Min Act: -0.0003

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4723. Min Act: -0.0003

Data Index: 604784 (C4 (Web Text))

Max Activating Token Index: 798