Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0638. Min Act: -0.0001

Data Index: 552727 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1000570 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0610. Min Act: -0.0001

Data Index: 574746 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0575. Min Act: -0.0001

Data Index: 482964 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0577. Min Act: -0.0001

Data Index: 928002 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1175806 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0583. Min Act: -0.0001

Data Index: 491635 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0553. Min Act: -0.0001

Data Index: 279002 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0549. Min Act: -0.0001

Data Index: 654582 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1300988 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0544. Min Act: -0.0001

Data Index: 407627 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0535. Min Act: -0.0001

Data Index: 18953 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0535. Min Act: -0.0001

Data Index: 811321 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0534. Min Act: -0.0001

Data Index: 467101 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0528. Min Act: -0.0001

Data Index: 125016 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0510. Min Act: -0.0001

Data Index: 292050 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1128733 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0495. Min Act: -0.0001

Data Index: 944571 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0543. Min Act: -0.0001

Data Index: 611579 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0518. Min Act: -0.0001

Data Index: 162803 (C4 (Web Text))

Max Activating Token Index: 757