Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 24 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0006

Data Index: 101923 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0546. Min Act: -0.0006

Data Index: 783938 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0518. Min Act: -0.0006

Data Index: 1203390 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0506. Min Act: -0.0006

Data Index: 1328413 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0488. Min Act: -0.0006

Data Index: 584994 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0495. Min Act: -0.0006

Data Index: 848211 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0494. Min Act: -0.0006

Data Index: 76220 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1357806 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1013356 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0469. Min Act: -0.0006

Data Index: 887947 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0469. Min Act: -0.0006

Data Index: 57315 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0450. Min Act: -0.0006

Data Index: 553320 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1322543 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0452. Min Act: -0.0006

Data Index: 550452 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0457. Min Act: -0.0006

Data Index: 359623 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0446. Min Act: -0.0006

Data Index: 579837 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0439. Min Act: -0.0006

Data Index: 432243 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0433. Min Act: -0.0006

Data Index: 732096 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0441. Min Act: -0.0006

Data Index: 947491 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0445. Min Act: -0.0006

Data Index: 951947 (C4 (Web Text))

Max Activating Token Index: 550