Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5697. Min Act: -0.0000

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5793. Min Act: -0.0000

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5601. Min Act: -0.0000

Data Index: 974296 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5446. Min Act: -0.0000

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4970. Min Act: -0.0000

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1206147 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1269395 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4934. Min Act: -0.0000

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4743. Min Act: -0.0000

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4568. Min Act: -0.0000

Data Index: 96345 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4731. Min Act: -0.0000

Data Index: 83523 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4414. Min Act: -0.0000

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1062217 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4607. Min Act: -0.0000

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4662. Min Act: -0.0000

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4183. Min Act: -0.0000

Data Index: 363450 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4453. Min Act: -0.0000

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.5793. Min Range: -0.5793

Max Act: 0.4337. Min Act: -0.0000

Data Index: 414068 (C4 (Web Text))

Max Activating Token Index: 970