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

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

Neuron 4300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0000

Data Index: 417304 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1331703 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1066045 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0581. Min Act: -0.0000

Data Index: 14885 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0580. Min Act: -0.0000

Data Index: 842530 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1039376 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0510. Min Act: -0.0000

Data Index: 686010 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0473. Min Act: -0.0000

Data Index: 19452 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0459. Min Act: -0.0000

Data Index: 497286 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0451. Min Act: -0.0000

Data Index: 163504 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0466. Min Act: -0.0000

Data Index: 362652 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1148266 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0492. Min Act: -0.0000

Data Index: 965594 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0454. Min Act: -0.0000

Data Index: 780801 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0476. Min Act: -0.0000

Data Index: 432392 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0431. Min Act: -0.0000

Data Index: 96964 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0444. Min Act: -0.0000

Data Index: 349031 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1143801 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0405. Min Act: -0.0000

Data Index: 121312 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0418. Min Act: -0.0001

Data Index: 834534 (C4 (Web Text))

Max Activating Token Index: 129